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: 4, Informative) by Anonymous Coward on Monday June 29 2015, @03:30PM
I'd suggest grabbing a copy of turnkey node.js, you can get a webserver up and going in a few minutes. I recommend this because designing a web user interface is well established and tries to be friendly.
nodeJs turnkey iso: http://mirrors.dotsrc.org/turnkeylinux/images/iso/ [dotsrc.org]
nodeJs turnkey vm image: http://mirrors.dotsrc.org/turnkeylinux/images/vmdk/ [dotsrc.org]
You'll find lots of turnkey packages in the list, but nodeJs has 'modules' for deep learning artificial intelligences.
Once you have that up and going you can grab one of the modules for deep ai and figure out how to feed patterns in / get results from the module.
You can get a module from http://cs.stanford.edu/people/karpathy/convnetjs/ [stanford.edu] but there are many of them around.
(Score: 0) by Anonymous Coward on Monday June 29 2015, @05:34PM
That looks pretty good!