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) by erik.erikson on Tuesday June 30 2015, @02:46PM
This is where I spent my academic currency/time.
I would strongly suggest that you read Rethinking Innateness [https://books.google.com/books?id=vELaRu_MrwoC].
The field is stupid with big fancy names for minor alterations of the base learning rules or network generation/structuring strategies.
The mathematics are not too tough if you are willing to stare at a function and think through the layers of what it is asserting.
The commentor who mentioned overfitting to a training set provided fantastic commentary.