Fascinating.<p>Many years ago, when I wanted to become a programmer and I didn't know anything about code, I used to fantasize and be amazed by programs. Code was like dark magic.<p>This is how I feel today about machine learning. Neural networks, liquid state machines. It's wonderful voodoo to my eyes.<p>I hope one day I get to work in that field, it seems so useful for solving big world problems. I have notice a definite rise in articles being written and shared on HN about it lately, that's great.<p>For those completely in the dark, I found this library to have great wiki pages about the basics of neural network programming. Great read, I recommend it. <a href="https://github.com/cazala/synaptic/wiki/Neural-Networks-101" rel="nofollow">https://github.com/cazala/synaptic/wiki/Neural-Networks-101</a>
Reinforcement Learning is one of the most exciting areas of research in machine learning and AI going on right now in my opinion. It is going to play heavily in creating AI that can make decisions in dynamic environments.<p>A great introduction to the topic is the book Reinforcement Learning: An Introduction by Sutton & Barto. You can find the official HTML version of the 1st edition and a PDF of a recent draft of the 2nd ed. here: <a href="https://webdocs.cs.ualberta.ca/~sutton/book/the-book.html" rel="nofollow">https://webdocs.cs.ualberta.ca/~sutton/book/the-book.html</a>
In almost all real-time networks playing games, there's very high jitter in inputs. Even when the machine is moving straight, it's always very keen on doing some wiggling with the other keys.<p>My question is: Is it possible to eliminate that by further training? Naively you could drop 'stupid' inputs, but I assume that may also mess with the machine's understanding.
In the context of AI and gaming, I definitely recommend this series of three youtube videos:<p><a href="https://www.youtube.com/watch?v=xOCurBYI_gY" rel="nofollow">https://www.youtube.com/watch?v=xOCurBYI_gY</a><p>Some games are played better than human would.
A neural Network is specializing in one particular problem set? You can not create Meta-Neural networks that reconnect the specialized Networks or grow new ones?