I'm a neuroscientist in a doctoral program but I have a growing interest in deep learning methods (e.g., http://deeplearning.net/ ). As a neuroscientist using MR imaging methods, I often rely on tools to help me classify and define brain structures and functional activations. Some of the most advanced tools for image segmentation are being innovated using magical-sounding terms like Adaboosted weak-learners, auto-encoders, Support Vector Machines, and the like.
While I do not have the time to become a computer-science expert in artificial intelligence methods, I would like to establish a basic skill level in the application of some of these methods. Soylenters, "Do I need to know the mathematical foundation of these methods intimately to be able to employ them effectively or intelligently?" and "What would be a good way of becoming more familiar with these methods, given my circumstances?"
(Score: 3, Interesting) by inertnet on Monday June 29 2015, @11:39PM
I don't believe that single celled organisms make decisions by thought, it's just evolution at work. The ones with the correct response to a threat or food or whatever will survive. Those with the wrong response just die off. After 3 billion years this has gotten so complex that it might look like they're making decisions, but they're not.
(Score: 4, Insightful) by mhajicek on Tuesday June 30 2015, @12:31AM
How is that different from a human?
The spacelike surfaces of time foliations can have a cusp at the surface of discontinuity. - P. Hajicek