News for hackers. Stuff that matters.
Re:"Memory foam" approach to unsupervised learning by dsfsdfd on Friday October 16, 2015 @04:15AM (#10398077)
Yay, someone with the sophistication required is working on this! As I've been thinking for a few years, intelligence is more about absorbing pattern from the world than it is about the deliberate process of constructing pattern from scratch within the system. It's is better to create a space where the pattern of the world can live, subject to some measure of objective utility, than it is to deduce some pattern from scratch using that same objective function.

God I would love to work in this field.

Re:"Memory foam" approach to unsupervised learning by gipp on Friday October 16, 2015 @09:07AM (#10398974)
You're just describing unsupervised learning; these guys are far from the only ones working in the field, and this is far from the most impressive approach. This is just time-averaged kernel density estimation, with an approachable metaphor attached to it.
Re:"Memory foam" approach to unsupervised learning by dsfsdfd on Monday October 19, 2015 @04:24AM (#10411766)
Dammit you appear to be correct.
Re:"Memory foam" approach to unsupervised learning by visarga on Friday October 16, 2015 @05:18AM (#10398246)
Cognition is pattern recognition, and we don't ever access the raw data, just the output labels - this is so Buddhist. In a sense we create our (inner) world because it is just patterns.
Re:"Memory foam" approach to unsupervised learning by baobabaobab on Friday October 16, 2015 @01:49PM (#10400914)
Recognizing patterns in data is so easy to do, that how easy it is, turns out to be a major problem in machine learning. You can always find some explanation that perfectly fits all the data you see, but that doesn't mean it will fit the data you haven't yet seen.

The challenge is finding the simplest patterns that will generalize to explain the most data, while wasting as little effort as possible on the irrelevant patterns. In high dimension data, the number of possible relationships to analyze explode, you can find patterns everywhere you look, so it's deciding where to bother looking with your limited resources that's hard.

That patterns are nothing special doesn't seem obvious to us because, evolution has done a pretty good job solving this problem(in the domain of inputs we evolved to deal with), and we only perceive those patterns that are likely to generalize.

Re:"Memory foam" approach to unsupervised learning by eli_gottlieb on Friday October 16, 2015 @02:13PM (#10401083)
"What lay behind the illusion of the park was just the real park."

So no, not that Buddhist. The function of cognition is not to detach ourselves from an insignificant, not-really-there illusionary world, but in fact to create increasingly accurate, but still tractable, "illusions" that let our brains draw closer and closer to the real world.

Re:"Memory foam" approach to unsupervised learning by dsfsdfd on Friday October 16, 2015 @05:23AM (#10398261)
Exactly. I'm secretly thinking that some of the reason we have failed so far at general AI is we are coming at the problem from a western philosophical tradition :) Nice to meet you brother
Re:"Memory foam" approach to unsupervised learning by aleh on Friday October 16, 2015 @05:07AM (#10398218)
What you say about intelligence vaguely resembles genetic algorithm... or I just saw a pattern similarity where none exists :)