Today is full of minor little administrative details that need attention and always seem to correlate with 1) the beginning of the classes and 2) returning to Austin after having been away all summer. The end result of all of this is that my mind is all over the place right now, and not nearly [...]
David Vernon’s opening keynote at this year’s ICDL included a lot of information about the iCub, a serious effort to create a standard platform for developmental robotics. The talk was in part a review of a road map for developmental robotics that iCub researchers have been working on. They have a compelling story, one that I find very interesting. After [...]
In a previous post I mused on the recent proof attempt. As a practical matter, complexity theory is very different from what I do, so even though I’m a graduate student in computer science, my ability to comment on the internal dynamics of the discipline is quite limited. My opinions are really a result of [...]
… in the 1960s almost no one realized that machine vision was difficult. The field had to go through the same experience as the machine translation field did in its fiascoes of the 1950s before it was at last realized that here were some problems that had to be taken seriously. The reason for this [...]
I saw the following “proof” (meant to illustrate — not as a serious claim) that in these slides. Suppose . Then clearly for all oracles . Since we know that for at least one oracle , it follows that .
In a previous post I was a bit inaccurate when trying to make a point about the kinds of complexity issues that arise when dealing with practical problems in AI. I stated that human vision accomplished object recognition using constant depth circuits. Memory plays a role in object recognition, so characterizing the human process of [...]
In fact, the nuts and bolts of A.I. research can often be more usefully interpreted without the concept of A.I. at all. For example, I.B.M. scientists recently unveiled a “question answering” machine that is designed to play the TV quiz show “Jeopardy.” Suppose I.B.M. had dispensed with the theatrics, declared it had done Google one [...]
… or how important is that problem really? There’s an interesting attempt to prove floating around. The best set of initial reactions seems to be here. Beyond the absolute basics, I can’t evaluate what’s going on with the proof, and anyway it seems like most of AI is predicated on the assumption that so we [...]
What is an object? UPDATE: This is such a general question, I thought it might be worth providing a specific example. In the dominant paradigm of computer vision research, an object is an array of pixels with a particular label. The main research challenge is identifying some model that explains the variations in pixel arrays [...]
Given some uncertainty about the state of the world, what action can I take to minimize my uncertainty? Given a model of the world, what action can I take in order to improve the model the most?