SoylentNews is people
SoylentNews
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?"
Original Submission
(Score: 0) by Anonymous Coward on Tuesday June 30 2015, @09:46PM
I used artificial intelligence as an umbrella term, and from my reading machine learning is a set of computational statistical methods (e.g. logistic regression). Artificial intelligence is the pursuit of "intelligence" what ever that means, by artificial means, which often will include machine learning methods. All these objections sound like needless hairsplitting to me which matter little to anyone other than the ones in the AI and the machine learning university departments.
(Score: 0) by Anonymous Coward on Wednesday July 01 2015, @12:47AM
I think you are wrong to ignore the distinction. Using your vague definition of "artificial intelligence" would allow any kind of updating procedure to be classed as such. People would not call gradient decent or mcmc examples of intelligence. They are just algorithms that compare different models to data and choose some as "best" according to some preset criteria.
(Score: 2) by mtrycz on Wednesday July 01 2015, @08:37AM
You are welcome.
In capitalist America, ads view YOU!