On Wednesday 16 May 2007 11:14:57 am Kingma, D.P. wrote: > John, BTW, it's Josh... > I'm particularly interested in the types of pattern mining you're planning > to perform, the types of patterns you think are necessary to search for > (spatial, temporal, causal, etc), and which search techniques you're going > to use given time constraints. But I guess you will release more information > as the project continues.
There is a fair stock of clustering and mining techniques, of which for a first crack at the problem I'm looking at affinity propagation and Kohonen maps. However, there is also the technique of having a set of pre-written transforms (e.g segmentation on pictures, Fourier transform on sound) that one can search for useful combinations of with a GA or the like. > The brain does not use images for representation, except tiny patches in > the very 'lowest' regions in the visual cortex. Representation is abstract, > distributed. You could read "Seeing and Visualizing: It's Not What You > Think" by Zenon W. Pylyshyn for a comprehensive synthesis of research and > theory. Rem acu tetigisti! For those who think that we think in actual pictures, here's an exercise: imagine two ordinary gears, meshed, and turning. Let's say they are the same size and each one has 17 teeth. Got it? Okay, watch carefully as they turn. What shape are the cogs (teeth)? Do the cogs roll across each other's face or slide? What is the shape of the path taken by the contact point? Or, imagine a planetary gear setup. The sun gear has 12 cogs and there are three planet gears, each of which also has 12 cogs. How many cogs on the annular gear? Don't calculate, *count them* in your picture. Imagine the annulus is stationary, and the sun gear drives the mechanism so that each planet makes a complete revolution and returns to its original position. How many times did the sun gear turn? Don't calculate, *watch the picture.* Doesn't work, does it? Pylyshyn points out that the number of primitive trackers we have for objects in the visual field (he calls them FINSTs) is tiny, something like 4 or 5. We don't really see in complete pictures when we're looking at something, much less when we're imagining it. Josh ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&user_secret=fabd7936
