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: 1, Informative) by Anonymous Coward on Tuesday June 30 2015, @09:18AM
Different AC. The above is true, only a very small percentage of people doing medical research (I include neuroscience here) know calculus, or much math at all. Even basic stats concepts, logic, and philosophy of science are all rare. It is not good, they have trained an army of lab techs who have trained a new generation of lab techs with no time/inclination to do anything but perform the null ritual. It is not that the researchers are dumb, the training programs are just very misguided. It is just bizarre that people studying dynamic networks have received no training in the tools developed hundreds of years ago to describe such phenomenon.
It's frustrating to have to explain every concept to every single person before even getting to the point (whats a binomial distribution, whats the difference between standard error and standard deviation). Or more likely, people won't even ask what you're talking about.