Mens Forma

More from the slime mould department

2006-12-06T02:15:00.000-05:00

And then there's this, which tops even the Roachbot.

Intelligence without Representation II

2006-12-06T01:56:00.000-05:00

From the article:

Japanese scientists claim that amoeba-like organisms have a primitive form of intelligence, following an experiment where a slime mould found its way through a maze.

Reporting in the journal Nature, Toshiyuki Nakagaki from the Bio-Mimetic Control Research Centre in Nagoya showed that a slime mould negotiated the shortest route between two exits in a maze, avoiding three longer paths.

"This remarkable process of cellular computation implies that cellular materials can show a primitive intelligence," Dr Nakagaki said.

I think this supports at least two things: one, Brooks' idea that intelligence with representation is not only possible but is also biologically based; and two, that Newell and Simon's symbol system hypothesis holds up. I would definitely call the behavior of this slime mould--when taken as a unified system--intelligent, as it is able to search through a space efficiently to reach a solution. I think, as Brooks would say, that there is intelligent behavior emerging from simple interactions amongst subunits in the system.

(PS: Definitely take a look at the photo; it is very surreal.)

Intelligence without representation I

2006-11-26T22:33:00.000-05:00

Brooks seems to think that behavior based AI will be able to produce intelligence on the level of human intelligence without ever resorting to internal representations at all.

His approach is inspired by evolution, which he says spent most of it's time perfecting perception, "acting and reacting." The things that AI had been primarily concerned with - reasoning, problem solving, language - are very recent developments. So, he says that we should be focusing on acting and reacting before focusing on problem solving.

I think he's right. He's convinced me that we ought to be focusing our attention on acting and reaction without resorting to internal representations of the world. Many of the things we consider intelligent behavior can be produced this way.

But I'm not convinced that language, problem solving, and reasoning can be produced by Brooks' approach. When we communicate with one another or reflect upon our own intenal states, we need symbolic representations. Brooks says that the fact that we use representations when communicating to one another or for introspection is not sufficient grounds to conclude that we have any internal representations to produce behavior.

He might be right. But it's worth pointing out that Brooks's epiphany about abandoning representation came when he realized that the calculations needed just to move a robotic arm was just too complicated. A reactive system with a lot of sensory inputs was able to solve the problem - without the complicated calculations.[*] But what about language? Language is, by its nature, representational. I suspect that getting a system to use language would be simpler if the system had internal representation than if it didn't.

Consilience

2006-11-19T13:43:00.000-05:00

"Philosophers are beginning to like it—it's something for them to do. They've been sort of flopping around since the failure of positivism."
—Edward O. Wilson, in an interview with Seed Magazine (November 2006).

The article from which this quote was grabbed is about Wilson's latest book, The Creation, and the rift between science and religion. The book itself is Wilson's attempt to draw the two worlds together in a truce for the sake of humanity's progress, and more specifically to garner attention towards saving the Earth, rather than wasting breath on an argument that goes nowhere. This article is one in a series that spans newspapers and magazines—including Wired's "The Church of the Non-Believers"—that cover a series of books published this fall written by top scientists and philosophers on the subject of fundamentalist values overtaking scientific reason. The authors of these books include Richard Dawkins, Sam Harris, Daniel Dennett, and of course Edward O. Wilson.

The quote above is a reference to the central idea of his 1998 book, Consilience: The Unity of Knowledge, that all fields of knowledge and scientific inquiry are intrinsically linked by a set of fundamental rules implicit to all fields. His remark is in reference to the fact that, after decades of these fields dividing and splintering, there is recent synthesis and convergence where certain fields jut against one another. As members of one field identify similar ideas found in others, they initiate an exchange with their newfound colleagues, which include bridging gaps in each other’s knowledge and linguistic blending.

But doing so is a tedious process. Although the semantic content of related fields develops often along parallel routes, occasionally crossing paths, the syntactical elements progress divergently from the outset, and researchers find themselves unable to communicate effectively with cousins hailing from those neighboring fields. Wilson’s comment hits squarely upon the utility of philosophy emerging in the modern world.

Philosophers have a new task: as catalysts of fusion, to combine the reactant disciplines of science and merge them together into novel, nascent branches of inquiry. Science becomes fragmented as scientists delve deeper into the disparate wells of knowledge, but the philosopher may quickly traverse the many beaten paths, picking up the shards along the way. To fit them together is to fill in the semantic gaps of each domain—and in doing so there occurs a reformulation of content in a new syntax adaptable to the various extant fields, thereby joining them in linguistic solidarity.

PS: For the text of a discussion between E.O. Wilson and Daniel Dennett, click here.

The Life and Times of William Sidis

2006-11-15T00:16:00.000-05:00

Perhaps there is such a thing as being too intelligent.

"At age nine William attempted to enroll at Harvard, and though the entrance exams were not a challenge for the young intellect, he was turned down on the basis that he was too 'emotionally immature' for college life. As William waited for the Harvard admissions board to capitulate, he spent the intervening time at Tufts College correcting mistakes in mathematicians' books, perusing Einstein's theories for possible errors, mastering foreign languages, and diligently collecting streetcar transfer slips."

"...he died a reclusive, penniless office clerk."

The moral of the story that I draw from this is that if there are Laplacean Martians that exist, they wouldn't want to spend more than a few minutes with beings that lack any perceptible intellect such as ourselves. And if one of them ever ended up being stranded on Earth with us, it would probably die from the feeling of being crowded by stupidity.

Giving Rise to Semantics

2006-11-12T18:01:00.000-05:00

I want to start out by explaining what my idea is and is not. First of all, this is not a complete theory of mind; I think it lends itself to a possible theory, but by its lonesome self it is not something that should spur anyone to run out to a computer lab and start programming. As a matter of fact, as I’ll note in places, there are points where I want to gather empirical evidence.

Second, this is not meant to refute or bolster Searle’s argument. What I am doing here is considering the conclusion of the Chinese Room Argument to be, It is not clear how syntax can give rise to semantics. Searle would of course claims it is impossible, but I think it is more prudent to just stop by saying that we simply don’t know if it is possible, and if it is, then we don’t know how.

Third, what I am addressing is the question, What else could it be? I am trying to offer here a possible alternative to a Turing Machine. Now, two questions seem to arise immediately from my saying this: (a) Am I actually saying that the syntax of a Turing Machine can’t give rise to semantics; and (b) Am I saying that my alternative is actually what gives rise to semantics? My answers: No, and no. I do not know if TM’s can or cannot give rise to semantics, and in fact I think that it’s difficult if not impossible to prove one way or the other at this time with the knowledge that we currently have. In other words, I claim temporary agnosticism. Also, my alternative that I am proposing is by no means a definite solution, only what I believe to be a possible solution. I think that it would be as difficult to prove one way or the other the feasibility of my solution as that of a TM.

If the thought crosses your mind that my argument will be for naught if it doesn’t offer a conclusive insight, then rest assured, as I believe there is a specific, non-arbitrary set of empirical evidence that is required to make my theory complete, some of which has already been gathered. To that effect, part of the conclusion of my idea here will be a plan for future study of various subject matters.

***

With that out of they way, here is my idea:

As described by Minsky, a Society of Mind is necessary and sufficient for having/making a mind.
The massively parallelized multi-agent system that comprises the mind cannot be emulated by a single TM.
Following 2, the reply by Searle (Mooney’s Reply H) that Minsky’s Society (being a “connectionist architecture”) can be reduced to a single TM does not apply.

Now clearly, I must justify 2. Obviously, a single TM can emulate multiple TM’s in parallel. I previously brought up my example of an eight-core processor being emulated by single-core to demonstrate my belief in this.

The reason why, then, a single TM cannot emulate a society of Minsky’s agents is because there is something that these agents bring with them that can at best be only simulated, and not emulated. This is an important distinction here: I mean by emulation just what I meant before—that implementing multiple TMs or an architecturally different TM on a single TM is wholly, utterly, and completely equivalent (albeit computationally slower); I mean, however, by simulation a proximal functional equivalence.

Notice how I did not apply “functional” to the definition of emulation; it is not merely functionally equivalent, but rather it is a one-for-one equivalence on the lowest level of operation (namely the manipulation of symbols). Simulation, then, is hindered by the fact that (1—which by itself would not matter) it is not operationally equivalent and that (2) it can only approximate the behaviors and solutions of that which is being simulated.

So what is it about Minsky’s society that cannot be emulated by a TM? It is the environment in which the agents operate. As I envision it, the system that comprises these agents is not one single unified structure, but numerous disparate structures that connect and disconnect to and from each other in a particular medium of interaction. This medium, I maintain, should not be overlooked, and in fact cannot, as this medium in which the agents persist plays an equally important role in determining the total state of mind system.

There is a recursive dynamic generative relation^* between an agent and its environment. In any interaction between an agent and its environment, the state of the environment will determine the state change made by the agent, and so the state of the agent will determine the state-change of the environment. Thus, any state of an agent, S(a), will be determined by two factors—the previous state of the agent, S(a-1), and the state of the environment S(e). And yet the same is also true of the state of the environment, as its change in state is determined by its previous state and the state of the agent.

Now, the important point, when I make the claim that this cannot be fully implemented on a finite state machine, is that the environment is continuous. The agents themselves may be discrete—meaning they have a finite number of states—but the environment in which they persist and operate is continuous—meaning it has an infinite number of states. The best that a discrete state machine can do is to simulate the environment.

This makes sense, conceptually. The agents are not in constant communication with one another; connections may be broken, lost, and then found again. Or signals may still be sent and received, but only through this dynamic and continuous medium of exchange.

Searle complains that it is not possible for syntax to give rise to semantics, as there is no clear moment in process of manipulating symbols that could suddenly be decided as crossing a threshold to semanticity. Because any sort of discrete state machine can be implemented on another, even the most complex of machines can be reduced to a simple structure of the most outlandish composition, be it beer cans and string or Chinese symbols and a naïve English speaking man.

So, since it is not clear how any system with a finite number of configurations of symbols can have semanticity, then perhaps it is necessary for it to have an infinite number of configurations—but not of symbols. The environment in which these agents operate would preserve and contain non-symbolized information, emitted from the agents themselves and from the external world.

This brings us to an important point: a TM loses information when it assigns symbols. Such is the nature of a discrete machine operating in a continuous world.

Perhaps, then (and this is my argument in all its glory), in order for a system to have understanding it must preserve information that would otherwise be lost in a purely symbol manipulating machine. The environment in which Minsky’s agents operate would have the capacity to do so, as it is continuous and may be in an infinite number of states.

Now, clearly, I am lacking knowledge in the subject of neurophysiology. Searle holds that only brains cause minds, but this does not give us any clear way to abstract away the specific biochemical activities exhibited by the brain. In citing the environment as a structure in which total information may be preserved, I believe that a clear to road to embark upon research can be shown.

Of course, as I wrote before, this is not even a partially complete theory, but merely an idea. I might be entirely wrong on this, as I might discover upon reading material on neurophysiology that the brain is a wholly unified structure with no “gaps” or “spaces” in it essential to its operation. However, from the little I do know, I am led to believe that the idea I have laid out is a relevant, and that such an environment can contribute to the dynamics of the whole system in a way not otherwise possible.

^*I owe this phrase to Mpodozis, Letelier, and Maturana

***

I just want to tag this on, here at the end, for purposes of cognitive mastication:

"The behavior of an agency is therefore determined both by its internal connection pattern and state, and by its external environment, as reflected by the input signals."

Link

First Impressions of Connectionism (Rumelhart)

2006-11-11T22:54:00.000-05:00

With this article we move away from asking what is theoretically possible (can machines think?). Instead we presume that we can design thinking machines, but wonder how to make the problem tractable.

Connectionism offers a methodology that seems to correspond well with the way human minds work. It moves away from the von Neumann model of computation to a model that Rumelhart calls "neurally inspired." Proponents of connectionism claim this model is condusive to the sorts of algorithms that will be needed to design intelligent machines.

The shift in architecture doesn't change what is theoretically possible. A von Neumann computer can emulate other architectures; any algorithm can be computed by any Turing Machine. But the change in architecture does lead to a change in how we model cognition. We know that changing paradigms can have potent effects. When programmers shifted to the structured programming paradigm, they were capable of meeting the demands that sophisticated software systems made of them. Without the paradigm shift, it's probable that they would be unable to program software at the level of complexity that is currently produced. Designing the complicated systems they do now would have been theoreticaly possible prior to adopting the structured programming paradigm, but it wouldn't have been practically possible.

It's worth noting that AI had for a long time been dominated by the LISP programming language. Like connectionism, LISP does not model the von Neumann architecture; so, I don't think AI has been using the von Neumann architecture exclusively until the arrival of the connectionist model. What distinguishes connectionism from GOFAI the most is how it models knowledge representation. In connectionism, knowledge is represented implicitly in the system, as opposed to the explicit representation of GOFAI.

The implicit representation is a "pattern of connectivity" of the smallest processing units in a connectionist model (these small processing units are analogous to a neuron). These neurons are connected to each other by various weights. This pattern of connectivity can be represented as a matrix that Rumelhart calls a"connectivity matrix."

And now some ramblings:

The matrix sounds exactly like an adjacency matrix used to represent a graph, with the smallest processing units the nodes. I don't know if it's helpful, but changes from one pattern of connectivity to another can be formalized, mathematically, as a multiplication of the connectivity matrix C at time t by some transformation matrix T. So that C(t+1) = C(t) * T (Rumelhart showed a similar formula for when individual nodes are activated). Playing around with knowledge representation in a connectionist model is "just" playing around with an adjacency matrix.

Researchers Create Artificial Retina From Silicon

2006-11-07T18:26:00.000-05:00

I came across an interesting article today about artificial retinas.

From the article:

Researchers from the University of Pennsylvania and Stanford University have made a breakthrough in the field of vision. Kareem Amir Zaghloul and Kwabena Boahen have proposed a silicon retina that reproduces signals in the optic nerve, a technology which could be used to provide vision to those who suffer from blindness-related diseases, such as retinitis pigmentosa

. . .

“We morphed our retinal model into a silicon chip by replacing each synapse or gap junction in our model with a transistor,” Zaghloul and Boahen revealed. “One of its terminals is connected to the pre-synaptic node, another to the post-synaptic node and a third to the modulatory node. By permuting these assignments, we realize excitation, inhibition and conduction, all of which are under modulatory control.”

It's too bad the article doesn't explain how everything works, but I suppose that's a good reason to read the journal article and take a neurophysiology course and an eye anatomy course.

Searle vs The Minds I

2006-10-30T02:00:00.000-05:00

The Myth of The Computer

The Myth of the Computer: An Exchange

The exchange between Searle and Dennett and Hofstadter in the New York Review of Books gets personal! I believe I found that quote about Searle Professor Chopra was searhing for, though it was Dennett not Hofstadter who wrote it.

The quote is a response to Searle saying, in regards to the Chinese Room argument:

The mental gymnastics that partisans of strong AI have performed in their attempts to refute this rather simple argument are truly extraordinary.

Dennett responds:

Here we have the spectacle of an eminent philosopher going around the country trotting out a "rather simple argument" and then marveling at the obtuseness of his audiences, who keep trying to show him what's wrong with it. He apparently cannot bring himself to contemplate the possibility that he might be missing a point of two, or underestimating the opposition. As he notes in his review, no less than twenty-seven rather eminent people responded to his article when it first appeared in Behavioral and Brain Sciences, but since he repeats its claims almost verbatim in the review, it seems that the only lesson he has learned from the response was that there are several dozen fools in the world.

Damn!

In Searle's review of The Minds I, he claims that Hofstadter and Dennett fabricate a quote which "runs dead opposite" to what he was trying to convey in his paper on the Chinese Room argument.

The quote? Instead of quoting Searle as having said "bits of paper" they misquote: "a few slips of paper." I have to agree with Dennett that the misquote hardly constitutes a fabrication that conveys the opposite opinion that Searle holds. In his response, Dennett apologizes for the misquote, and promises that the mistake will be corrected in future editions of the book. I can verify this: my copy, which dates from November 1982, correctly quotes Searle.

The Systems Reply

2006-10-30T00:35:00.000-05:00

Take a Turing Machine that takes as input a story in Chinese, followed by a set of questions in Chinese. It is constructed to produce, as output, answers to the questions, in Chinese. The answers are meant to be coherent responses to the questions. The Turing Machine is so well constructed that a native Chinese speaker will believe the responses come from a Chinese speaker.

We might think the Turing Machine understands Chinese.

Take a man, who doesn't speak any Chinese, sitting in a room. He's given a story in Chinese as input, a set of questions in Chinese, and a set of instructions on how to produce, as output, answers in Chinese. The answers are meant to be coherent responses to the questions. The man in the room performs the instructions so well that a native Chinese speaker will believe the responses come from a Chinese speaker.

The man sitting in the room does not understand Chinese.

The Turing Machine is a symbol manipulator. So is the man in the Chinese Room. So, the argument goes: if you accept that the man doesn't understand Chinese, then you must accept that the Turing Machine also does not understand Chinese.

The Systems Reply: while the man in the room does not understand any Chinese, the system taken as a whole does. The system consists of the man and his instructions, presumably in the form of "bits of paper," and perhaps a pen or pencil.

Searle says that arguing that the "conjunction" of the man with the "bits of paper" is capable of understanding, where the man alone is not, is absurd; he feels embarrassed to formulate a response to it at all.

The Turing Machine described above had its instructions - the rules by which it changed from one state to the next - built into its hardware. In the case of this Turing Machine, the Turing Machine itself was the system. The system consisted of: the tape head, and strip of paper on which it marked symbols. We wouldn't say that the tape head or the strip of paper is what understood Chinese, but the Turing Machine taken as a whole system that does.

The system in the Systems Reply, on the other hand, consisted of the man (and all of his constituent parts) and some "bits of paper." So it does seem different than the Turing Machine: it's easier to think of the TM as a single system that can be said to understand than it is to think of the man along with some "bits of paper" and a pencil as one. The TM, after all, is a single machine.

Let's tighten the analogy then. Take a Universal Turing Machine. As input it can take a description of any other Turing Machine, and run it. [Dennett and Hofstadter call this emulation to distinguish it from simulation. Emulation is exact since we keep a description of the emulated machine down to its lowest level states, unlike simulation which is an approximation which attempts to mimic the behavior of that which is simulated.] We feed as input to the Universal Turing Machine an encoding of the Turing Machine described above - the one that can produce output in Chinese so well that Chinese speakers will believe the output was written by a Chinese speaker. The rest of the story is the same: we the feed the UTM some text in Chinese, followed by some questions, and it produces as output Chinese text.

We might think that the Universal Turing Machine, taken together with the encoding of the Turing Machine that can produce Chinese output, understands Chinese.

The idea that the physical machine, the Universal Turing Machine, taken with some "bits of paper" as input (the encoding of the TM that produces Chinese output) does not seem absurd.

An the analogy is tighter: the UTM is analogous to the man sitting in the room; the "bits of paper" are analogous to the encoded Turing Machine.

Dennett says that Searle's argument is a mere "intuition pump" - there is no argument, only an attempt to play on our intuitions. Most people's first intuition is that taking the man with the paper as a system that is capable of understanding is absurd.

I claim that those same people would not find the idea of the Universal Turing Machine along with the encoded Turing Machine that produces Chinese output, as a system that can understand Chinese absurd. It's perfectly intuitive.

If you accept that the UTM taken together with the encoded TM can understand Chinese, you have to accept that the man taken with the bits of paper does too.

Micro-Intelligence

2006-10-25T01:13:00.000-04:00

I think that a popular bit of self-delusion that infects those who are interested in building a robot with a capacity for human intelligence is in the conception of what they envision the robot doing. Perhaps this is mostly a complaint against what Haugeland termed GOFAI, but it seems to me that following Turing’s example of giving the machine a specific goal to accomplish, many experimenters think to themselves, “what sort of thing do humans do that we characterize as an expression of intelligence?” and then set out to build a machine that does just that. For example: humans play chess and checkers, and that is a sign of intelligence; humans recognize objects and can form opinions on the properties of those objects, so that is a sign of intelligence; and even mundane tasks, such as navigating the hallways of a building to deliver a piping hot cup of coffee is deemed an activity for the intelligent, so a machine that can do that must in some way be intelligent.

The problem with building a machine that can “recognize” objects, have “conversations”, or play chess or checkers is that that is the totality of its behavioral range; its whole environment, meaning the objects it can “sense” and the dimensions across which it can exert any influence are contained wholly within a small scene of blocks, a small vocabulary (with little to no true understanding, to boot), or an eight-by-eight board with a variety of at most six different types of pieces. There is some sense that once one builds enough micro-worlds in which machines are able to operate—namely, one micro-world for visual recognition of objects (SHRDLU), one for language processing (ELIZA), and others for manipulation of pieces (Samuel’s program) one can plug them all into each other and have a machine that displays a wider range of behaviors. If the complaint is that it has a set of primitives too small, making it unable to assimilate information about complex shapes, complex sentences, or playing pieces never before encountered, then the solution is simply to program in more primitives—curved lines, templates for complex sentence structures, or a battery of more pieces.

This is the point on which I agree with Hubert Dreyfus the most heartily, but also after which we depart and go our separate ways. In regards towards those types of projects, he makes the argument that having once accomplished the construction of a machine that can carry out a set task, it is not remotely close to attaining any sort of human intelligence, for it is restricted to that one task alone and no other. Furthermore, the micro-worlds are simplified versions of environments and activities that we humans encounter and execute, but they are so stripped down as to be meaningless in the context of the real world. Dreyfus notes, “The nongeneralizable character of the programs so far discussed makes them engineering feats, not steps toward generally intelligent systems, and they are, therefore, not at all promising as contributions to psychology.”

Furthermore, plugging in micro-worlds to each other, and then manually adding in more primitives, would be equally pointless. The machine in question would still bear capabilities bounded strictly by its programming, meaning it does not grow or learn in the way a human does. In order to have the type of intelligence that we do, it must be able to form for itself new primitives, with which to compose a world growing ever more complex.

At this point, Dreyfus begins his critique of Minsky’s frameworks. Although I agreed with him regarding the micro-worlds, I strongly disagree with his general assessment of Minsky’s theory. It seems quite apparent to me how frames can lead to the formation of new primitives: our varying types of sensory inputs are stored in collections of nodes, which over time come to correlate with each other, whereupon they form frames consisting bundles of different types of information. For example, a baby encountering an apple many times over will come to correlate the redness, the smoothness, the hardness, and all other properties that can be sensed. With that bundle of information, the baby will then come to recognize other apples by virtue of similarities of their properties. Further properties of apples—such as behavior when falling, or rolling, or colliding with other objects—are assimilated with experience.

In his concluding main thesis, Deryfus makes the claim that the idea of knowledge representation is not only unnecessary but also is impossible to realize in any artificial system. Because an explanation of how we do something always traces back to what we are—which Dreyfus believes is something we can never know—we will never be fully equipped with the conditional rules for founding an intelligent system. “In explaining our actions we must always sooner or later fall back on our everyday practices and simply say ‘this is what we do’ or ‘that’s what it’s like to be a human being.'”

Furthermore, rather than representations, Dreyfus believes that intelligent behavior can be explained under alternative accounts: one, “developing patterns of responses,” with recognition being gradually acquired through training; and two, allowing for “nonformal (concrete) representations” (e.g.: images) that are used in exploration of “what I am, not what I know.”

Frankly, I couldn’t disagree with Dreyfus more. Based on the fact that we collect information with our sensory apparatuses, and then store it for later use, it must necessarily be represented in some manner—at all times. How else can we manipulate the information? Dreyfus might say that we should appeal to those concrete representations that don’t require any explanation of the rules for symbol manipulation, since there are no symbols in concrete representations. But how does this explain anything? What have we learned about ourselves from this? How does it allow us to explain our behavior and help predict future behavior?

Dreyfus’ “patterns of responses” seems to me to be a behaviorist denial of any internal life. For him, there seems to be no concept of swimming that we hold, only our acquired responses to being in the water. All we do in life is respond to stimuli.

Dreyfus seems wrapped up in the idea that to have intelligence is to have only human intelligence and therefore since no computer can be human, it cannot have intelligence. I would argue that there must be an entire range of ways to be intelligent, perhaps even some that don't use representation, as our intelligence as a species did not arise in a day or ten-thousand years, but evolved over millions of years (and how many hundreds of millions of years ago was it when the most primitive nervous systems emerged?). Clearly, then, there are some structures that evolved first and others that rely on those original formations; I take this as evidence that (a) cognitive science should begin to concern itself more with the evolution and development of intelligence and that (b) more experimental research should be done that does not try to go gung-ho and recreate a feature of human intelligence, but rather should attempt to recreate the intelligence of lesser species.

Avatars of the Tortoise

2006-10-17T02:47:00.000-04:00

In "Avatars of the Tortoise," Borges traces Zeno's paradox throughout the history of philosophy. Zeno argued that movement was impossible. Aristotle explains the paradox as follows: "In a race, the quickest runner can never overtake the slowest, since the pursuer must first reach the point whence the pursued started, so that the slower must always hold a lead."

Borges reflects that the applications of the paradox are inexhaustable. He says, "the vertiginous regressus in infinitum is perhaps applicable to all subjects." One such application is, "the problem of knowledge: cognition is recognition, but it is necessary to have known in order to recognize, but cognition is recognition..."

He finds in Sextus Empiricus an argument for the uselessness of definitions, "since one will have to define each of the words used and then define the definition."

[[ I'll expand on the following at a later time. Right now I'm just sketching out an idea ]]

I'm reminded of Dreyfus and wonder if we find a little of Zeno in his argument. A key objection to Minsky's framework of knowledge is its inability to give a way of translating perception (what Borges called 'recognition') into formal representations (ie terminals in a frame). And the objection to using formal representions, in principle, to create intelligence is reminiscent of Sextus Empiricus's reasoning about the futility of definitions.

2006-10-15T17:29:00.000-04:00

Before posting some much belated responses to Dennett's paper on "True Believers" I want to address some issues about Turing's paper.

One of the objections Turing anticipates is what he calls the "continuity from the nervous system." The idea is that the human nervous is not a discrete state machine, and therefore it is not possible to mimic the behavior of the nervous system with a discrete state machine.

Turing's response to this surprised me. He says that "...if we adhere to the conditions of the imitation game, the interregator will not be able to take advantage of this difference."

Now, keep in mind that the purpose of Turing's paper is to support the claim that the imitation game is a valid substitution for the question "can machines think?" So his response that the imitation game won't distinguish an important difference between humans and discrete state machines suggests a lacking in the imitation game. The question is, which of the following are true:

a) the imitation game cannot make an important distinction and therefore is not a sufficient test, or
b) the differences between a continuous state machine and a discrete state machine are irrelevant when trying to determine if a machine can pass the imitation game, or
c) the difference between a continuous state machine and a discrete state machine are irrelevant when trying to determine if a machine can think

We can take for granted that (b) is true for the moment, after all Turing admits this, but I think what Turing was trying to refute is (a) and (b). If not, it's what he should be attempting to refute. See, the objection about the human nervous system was made by people who didn't even consider the imitation game - so that the fact that the differences between discrete and continuous machines doesn't do anything to effect the outcome of the imitation game does nothing to refute the original argument. It's up to Turing to convince us that even though the imitation game is not affected by the differences between a continuous state machine and a discrete state machine, the imitation game is still a good substition for the question about intelligent machines.

All of this about discrete state machines vs continuous state systems led me to consider some questions Turing did not address.

There is evidence from quantum machanics that the universe is discrete. So that, on some level, the nervous system is itself discrete. Assuming this is true, the discreteness of the universe would only be true "at the atomic or subatomic" level, but the fact remains that we can give a discription of the universe in terms of a discrete state machine. Which, as we know, means that any other discrete state machine is able to simulate it (run it) - given a enough time and memory. So, if it were proven that that the universe is discrete, we would know, with certainty, that a computer could simulate intelligent systems, because intelligent systems exist in the universe.

Of course this would only be interesting from a theoretical level, since the amount of memory and speed needed would make the problem of actually simulating the universe (or any physical description at such an atmic level) intractable. Also, we would have a situation in which the intelligent systems exist on the machine - but the machine itself (taken as a whole) is not an intelligent system any more than the universe itself is. The machine would be simulating the entire universe, in which intelligent systems are only a fraction of what it's simulating; the intelligent systems might be thought of as virtual machines that our real machine is simulating.

Once we know that it would be theorectically possible for intelligence systems to exist on discrete state machines in this way (which is up to quantum machanics to prove) we'd know that it *can* be done, perhaps without the need of simulating everything in the universe.

My other question is related: can a discrete state machine simulate any continuous system? I'm not sure if it theoretically true that one can, but it seems that given enough precision a discrete state machine can become accurate enough for the fractional differences between it and the continuous system it is simulating to be irrelevant.

In fact, the extent to which the discrete state machine is sucessful in its simulation is probably determined by the degree of accuracy being demanded. It can always be better, since it can always be more precise - infinitely more precise, since we're attempting to simulate a continuous system. (Are discrete state machines by definition finite? I don't think so, since the theoretical Universal Turing Machine is infinitely large, and certainly discrete. But, on the other hand, we can never build an actual Universal Turing Machine).

If it is true that the universe is actually discrete, not continuous, but that we think of the human nervous system as a continuous system, then it follows that a discrete system (the quantum universe) is simulating a continuous system (the human nervous system). Simulation probably isn't the right word here...but it's meant to suggest that if the universe can go from discrete to seemingly continuous, then we can do it too.

2006-10-13T03:12:00.000-04:00

[Note: I'm going to clean this up, because I've decided it's not very readable.]

My Roommate has iTunes.

I can get into his iTunes from my computer, but only if we’re on the same network. If I’m outside of the network—say, at work in the library, trying to connect to his computer—it will not allow me to access his songs. This way, Apple doesn’t have to worry about crossing any copyright boundaries. However, if I SSH into my home computer, I can then control that it and have it connect to my roommate’s iTunes.

It’s like being at the door of a club, where on the outside its dark and frigid, on the inside it’s hot and noisy, and the only access you have to it is mediated by the bouncer who opens a slit in the door.

Returning my thoughts to mind design…

I can think of a node in a network being activated, and as part of its activation, it is given a signal to activate all connected nodes to a depth of n, and it then activates all of its adjacent nodes to activate them, sending with all activations a signal of n - 1. Each node in this cluster of the network behaves the same, so the signal travels down to a level n from the origin.

Furthermore, each node is being given a request sent to it from the “higher” node—with information that acts as a certain criteria. If the information contained in the node meets the criteria, then it returns a tidy package of information appended to a list of information received from all the connected nodes to a depth of n.

The higher nodes, thus, have no direct access to nodes lower than one level down; the only access they do have is to one node down, one up, and other nodes at the same level. A node moves up the hierarchy by gaining more sub-nodes.

When I connect to my computer at home from work, I’m interfacing directly with a node below me, but the only way to retrieve information from sub-nodes of the computer is to use it to mediate the information. I am also a node, where information is requested from me, with a certain criteria, and also signaling to me how far I should look. It is as though the computer performs a certain function for me, which is to respond with certain information; being myself a node, I don’t become concerned with how the computer gives me the information that it does, only that it does.

I can imagine a network of nodes based off of an image. Nodes are generated serially by streaming through the pixels one at a time, saving the values of the pixels as information stored in the nodes. Nodes are clustered together first by their proximity to each as seen in the image; they then form a hierarchy based on how many nodes share the same color, with the nodes in the largest clusters of same colored nodes rising to the top. Nodes that are isolated, meaning no nearby nodes share similar colors, become relatively low level.

This can be accomplished by having the nodes, once they establish links to their neighbors, send out a signal to infinite depth, with the criteria that the receiving node needs to be the same color. Thus a node will assign itself a ranking based on how many nodes respond to it. Clusters of nodes that are the same color and continuosly connected to each other are then assigned higher levels by being unique among other clusters found in the given image, either by having a certain color found rarely elsewhere in the image, or by being the most luminous, etc.

Therefore you can have rough representation of an image using nodes in a network.

The whole network that corresponds to an image can then be thought of as one of Minsky's frames, with objects found in the image as terminals, represented as high level clusters of nodes (“capitals”) that share common features (color/luminosity). Of course these terminals will connect to others outside of the image (perhaps another image, or a linguistic frame), as this is a highly interconnected society of mind.

2006-10-10T00:44:00.000-04:00

Newel and Simon restate and old definition in a different light—intelligence is finding a solution to a problem, but specifically by traversing a search space. This seems sensible; any behavior we exhibit can be encoded as a set of actions. Learning might be described as acquiring new solution sets to problems. Theorizing might be described as producing partial solution sets. Producing a search space involves establishing what in the environment is mutable and what is immutable, and how things mutable can change.

In the example of finding a solution to ax + b = cx + d a (good) solution generator would need to first identify what in the environment (this being a brow-raisingly small environment) is mutable and how. But first it must identify the rules of the environment, namely that anything done to one side must be done to the other; then the specific changes can be identified—ax, b, cx, and d can all be added, subtracted, multiplied, etc. From there, a generator can produce solutions.

So what would happen if we considered a more robust problem? Let’s consider the problem faced by a chimpanzee trapped in a room with a hole in the ceiling and some sturdy boxes in the corner. The obvious (to us and perhaps the chimp) problem is how to get out of the room? First the chimp would have to identify what in its environment is mutable—namely, the boxes and itself. Of course, it might also have to actually go over to the boxes and determine physically if the boxes are light enough to move and strong to bear the weight. But anyway, once the variables are all determined, the generation of solutions may commence. The difficult question is, then, why is it so painstakingly obvious to us that the clear solution is to place the box beneath hole?

The answer to that, according to Newell and Simon, is a heuristic. And according their main thesis, intelligent behavior would be to follow some heuristic that produced a solution with the least searching. But what heuristic is it that we follow when figuring out how to get out of the room? More importantly, how does a machine develop such a heuristic on its own?

2006-09-24T00:58:00.000-04:00

Daniel Dennett’s paper is an inquiry into how humans are able to formulate predictions of the behavior of objects and other beings.

The physicalist stance is a strategy that is the most rigorous and robust; it is more or less deduction by accounting for physical properties of an object. This strategy works well for simple objects in our world, such as bowling balls, falling pianos, and spring boards, but does not work well for predicting the behavior of more complex objects such as frogs or butterflies, much less human beings.

The design stance is a strategy taken by one who supposes that a certain object is designed to behave in a certain way. This works well for all sorts of kinds of equipment and electronic devices, since we are able to infer its behavior according to a designer’s intent.

The intentionalist stance, which is the focus of Dennett’s paper, is taken by the one who assumes that the object, acting in its own self interest, has beliefs and desires that it will follow through on. This works so well, because being rational agents ourselves, once we are able to attribute those beliefs and desires, we are then somehow able to simulate their behavior based on our own.

I am convinced that the intentional stance is exactly what happens, as we often—especially during childhood—attribute beliefs and desires to anything and everything we see in the world. I might, if I so choose to, attribute beliefs and desire to my faucet; it leaks when it’s sad and gets too hot when it’s angry. Of course that’s ridiculous, but I can do it all the same, and I can certainly imagine it turning its spout up at me and say, “Why not? I have feelings, too.” Perhaps in some alternate, Roger Rabbit universe, it might spit in my eye if I think anything less of it. This certainly gives me “reason” to treat it with respect. This kind of reasoning, as I remember it, is very much alive in childhood where we do not have the capability to use a physicalist stance.

I think that this sort of reasoning might even be the cause for many if not most religious beliefs; people attribute beliefs and desires to nature, and when they predict its behavior they take those into account. Why upset nature, when she might lash back at me? I should follow God’s wishes in order not to anger him. One might be inclined to turn to the Gaia “hypothesis” because it offers an easy way of predicting the Earth’s behavior.

I disagree with Dennett on only two points, and they are perhaps small. The first is that I would not consider a thermostat to be an intentional system. I’m not sure what he means when he says that thermostats have representations of their environments, but I cannot imagine a thermostat as it is with any sort of representation. It doesn’t even hold information about its environment in the first place. There might be some rudimentary programming that can be done on it to change its behavior (such as, stay a little bit warmer in the morning), but there is no representation at all. It doesn’t “measure” anything about its environment, and thus there is nothing to represent. It reacts to a change in the atmosphere mechanically, without storing any information regarding that change. A vile of mercury inside of it reacts, directly causing a switch to be turned, which sends a signal to the boiler. What representation could possibly be going on there? But that’s a trivial point, anyway.

Second, I see the “language of thought” as a strong possibility, but I would add a clause. Dennett argues for its existence because he sees no alternative for a form of representation in our minds. We have mentalese to represent, symbolically, reality, and thus use symbols in some sort of logic natural to our minds.

I find no fault with the idea of mentalese and admit that it could possibly be true. But I do disagree that it is the only possible representation of the world that we carry; it seems fairly self evident to me that we have a robust graphical representation of the world. We are able to rotate three dimensional objects with our mind, which involves no symbolic manipulation. I think that from this graphical representation do we extricate beliefs and desires, which themselves may be represented symbolically and manipulated according to our innate rules of logic.

2006-09-16T18:28:00.000-04:00

Turing's proposal in "Computing Machinery and Intelligence" is often framed as: to determine if a particular machine thinks, have it play the Imitation Game, and if it passes you have sufficient evidence to believe that it does. But Turing is actually proposing that we substitute the question "Can machines think?" (Q1) with the question "can digital computers pass the imitation game?" (Q2) Turing didn't say that Q2 is a means to answering Q1, but that Q2 is the question we ought to be asking. Turing even goes on to dismiss Q1 as being meaningless.

What I find confusing is that the remainder of the article is devoted to refuting objections to Q1 or Q2,
but never to refuting an objection to his proposal that we substitute Q2 for Q1. Turing also makes no attempt to justify his claim that Q1 is meaningless. And when I read the article, it always seems to me that Turing is taking the position of someone who feels Q2 is a sufficient means to answering Q1, not that Q1 ought to be dismissed...I'll proceed as if this might be true.

The "Argument from Conciousness" and some of "Argument from Disabilities" are attacks on the Imitation Game as a means to determining if a machine could think. The idea is that even if a machine could pass the test, we wouldn't know if it actually felt anything, or understood what it was saying, or that it even knew that it was participating in a game.

Turing responds that if we take this line of argument we'll be forced into a solipsist position. It's true that we wouldn't know if the machine "feels" or "understands," but we can't be sure of this about any human other than ourselves either. Observed behavior is the best we can do, and is almost always taken as sufficient (except by solipsists of course), which is why the Imitation Game ought to be considered sufficient as well.

Turing's response works well for phenomenological consciousness - we can't know if the machine can "feel" anything any better than we can know that another person can feel anything.

But when it comes to knowing whether a machine is capable of attributing meaning to the symbols it manipulates (a type of "understanding") we can do a lot better, since we have direct knowledge of the methods the machine uses.

Let's take an algorithm for addition that could be implemented by any discrete state machine, that works as follows.

Given the following:

111+11

The number of '1''s we see will represent a number - so that the three ones on the left of the '+' represents the number 3, and the two ones on the right represent the number 2.

Replace the '+' with a '1':

111111

and then remove the last '1':

11111

Which we can take to mean the number 5.

Try it again for another sequence ( 11+11 ---> 1111 )...

This will work for all numbers represented this way, and can be programmed into any discrete state machine.

The noteworthy thing about the algorithm is that the machine implementing it doesn't need to know what the characters represent. We don't have sufficient reason for believing that a machine that implements this algorithm understands what addition is, what a number is, or what it is doing.

If we programmed the machine playing the Imitation Game in a manner similar to the algorithm above, except that the goal is not is add two numbers but to pass the test, we wouldn't have sufficient reason to believe it was capable of understanding what it was saying.

Turing does address this. He says, in response to a general objection that a machine is incapable of doing certain things, that, "...if one maintains that a machine can do these things, and describes the method that the machine could use, one will not make much of an impression. It is thought that the method (whatever it may be, for it must just be mechanical) is really rather base."

But I don't think it is an adequate response. My example doesn't demonstrate that the machine doing addition is using a base method - just that there isn't sufficent grounds to believe that it understands what it is doing.

((I need to give this more thought, since the technique for addition humans are often taught to use in elementary school doesn't require an understanding of the numerals being manipulated. There are times we don't use any technique - like when asked to answer "what is two plus two?" But perhaps what we're using is a simple mapping between "two plus two" and "four", which also does nothing to demonstrate our understaning. So maybe we can't do any better than the machine following the algorithm above)).

I'll continue with Turing's paper in another post...

2006-09-06T21:02:00.000-04:00

Haugeland’s Essay and Understanding Animals

I don’t think that there’s much to say about most of Haugeland’s essay, as it is merely an introduction and overview to the rest of the book’s articles. As for the nature and meaning of “mind design” I’ve so far found it to be a study that uses philosophy to commune between psychology and computer science. Computer science was borne of philosophy and math, still tethered by the umbilical cord of logic; and psychology sprang forth from the same social and ethical philosophies that produced sociology and anthropology. It seems to me that one needs to be a philosopher in order to assimilate abstract concepts from psychology and mold them into concrete forms for computer science.

There is one section that’s worth mentioning, from the end of Haugeland’s piece. He writes,

“It seems to me that…only people ever understand anything—no animals and no artifacts (yet). It follows that…no animal or machine genuinely believes or desires anything either—How could it believe something it doesn’t understand?—though, obviously, in some other, weaker sense, animals (at least) have plenty of beliefs and desires.” (pp 27)

First of all, this seems like a completely disingenuous argument—he first makes a very strong claim about the intelligence of animals, and then backs off by supplying a “maybe it is so, but in a weaker sense.” How can we understand what he means when he gives such vague and slippery arguments? Furthermore, the bar he sets for understanding seems to be met by plenty of animals. In training chimpanzees to speak sign language, the chimps must have those proto-concepts, and they do indeed apply them correctly, as evinced by the fact that Washoe not only used words correctly and in appropriate contexts, but also taught her own children to sign. That “Not all psychologists agree that Washoe did acquire language” doesn’t seem to be detrimental to the fact that she had understanding, as “she had semanticity (understanding)” (see AS Psychology). If she was able to learn only 800 words or achieve only the grammar of a 3^rd grader, it does not mean that she had no understanding or intelligence, rather that she had less of it then humans do.

Furthermore, primates are not the only animals that can learn language. Parrots are able to learn words, and will learn despite any active teaching by the owner or trainer. One parrot, trained to know the words “apple” and “banana,” became familiar with pears as well, but was not taught any words for them. On one occasion, the parrot pointed a talon at one sitting next to its trainer and cawed “banapple!” The trainer looked at the pear, knowing what the parrot meant, and proceeded to try to teach it the appropriate word. Yet the parrot insisted on using its own word, having apparently judged it so based on its qualities, being intermediate between bananas and apples. (In fact, it seems appropriate, considering a pear’s softer texture and less tart flavor in comparison to an apple.) If that is not understanding, than what is?

[PS: The parrot example comes from the Scientific American Mind magazine, which is not free, and I was unable to find the sources that the article uses.]

2006-09-05T22:56:00.000-04:00

"Mind design is the endeavor to understand mind (thinking, intellect) in terms of its design (how it is built, how it works). Unlike traditional empirical psychology, it is more oriented toward the 'how' than the 'what.' An experiment in mind design is more likely to be an attempt to build something and make it work--as in artificial intelligence--than to observe or analyze what already exists. Mind design is psychology by reverse engineering." --John Haugeland

This blog will be the posting site of responses to a collection of journal articles on the topic of mind design. The journal articles all come from a book entitled "Mind Design II," edited by John Haugeland, and with various contributors from the fields of philosophy, computer science, and psychology.

Based upon bi-weekly meetings with Professor Chopra, Jonathan and Phillip will supply one response to each of two articles read for every meeting. This means that the two of us will write these two responses over the course of the two week interval, plus additional comments made on each other's posts and by Prof. Chopra. The responses themselves will also include references to outside material that critique the articles.

Additionally, the readings and postings will culminate in a 20 page essay on an appropriate topic.

Mind Design II Index:

"What is Mind Design?" John Haugeland.
"Computing Machinery and Intelligence," A.M. Turing.
"True Believers: The Intentional Strategy and Why it Works," Daniel Dennett.
"Computer Science as Emprical Inquiry: Symbols and Search," Allen Newell and Herbert A. Simon.
"A Framework for Representing Knowledge," Marvin Minsky.
"From Micro-Worlds to Knowledge Representation: AI at an Impasse," Hubert L. Dreyfus.
"Minds, Brains, and Programs," John R. Searle.
"Architecture of Mind: A Connectionist Approach," David E. Rumelhart.
"Connectionist Modeling: Neural Computation/Mental Connections," Paul Smolensky.
"On the Nature of Theories: A Neurocomputational Persepctive," Paul M. Churchland.
"Connectionism and Cognition," Jay F. Rosenberg.
"Connectionism and Cognitive Architecture: A Critical Analysis," Jerry A. Fodor and Zenon W. Pylyshyn.
"Connectionism, Eliminativism, and the Future of Folk Psychology," William Ramsey, Steven Stitch, and Joseph Garon.
"The Presence of a Symbol," Andy Clark.
"Intelligence without Representation," Rodney A. Brooks.
"Dynamics and Cognition," Timothy van Gelder.

Schedule of Meetings:

September 18: Chapters 1 & 2
September 25: Chapters 3 & 4
October 16: Chapters 5 & 6
October 30: Chapters ...
November 13: Chapters ...
November 27: Chapters ...
December 11: Chapters ...

Two of the sixteen readings will be dropped (making a total of fourteen). This post will be updated when a decision is made on what chapters to drop.