Login

Sign up

OR

Can't sign in? Did you forget your password?

x

Login


If you don’t have an account, click right here


Can't Sign in? Did you forget your password?

x

Please fill in these details

to create your profile


Click on the image to upload your profile pic

x
x

At Awaremonk, I hereby pledge that

I will not troll or abuse any member of the community.
I will be a good listener.
I will check my facts before stating them and attribute them as well.

x

Forgot Password?

Enter your email and we shall mail you the password reset link

x

Reset Password

Enter new password and confirm password

x

Science and Technology

Here we discuss, well, everything science! That includes research, new discoveries, applications of science in the world, science policy, Technology and innovation

Aditya Singh , Starting up. Just learnt before launch its ca Oct, 14 2016

Machine Learning and Deep Learning and why is so much different than recursion and backtracking (like Deep Blue chess computer)



Akshat Rao , Junior Scientist at BARC, Trying Awaremonk. Oct, 14 2016


Machine learning is a very broad category. In fact I'm fairly certain that recursion is largely considered to fall under that umbrella.

But to get to the bottom of your question, you can think about it like this: a recursion model will attempt to know every possible state and solution to a problem. Show the model any given chess board and it will be able to look into its memory, consider all possible next moves, and choose one that yields the most probable path to victory.

It seems pretty straight forward, that's what you would want a chess playing algorithm to do. The problem is that chess is a game with a lot of entropy (complexity) and so it's very inefficient to have the machine remember all possible game states. What would be better is if the algorithm could generalize, taking one chess board configuration from its memory and learning a lesson from it that it can apply to different scenarios.

Machine learning is a very broad category. In fact I'm fairly certain that recursion is largely considered to fall under that umbrella. But to get to the bottom of your question, you can think about it like this: a recursion model will attempt to know every possible state and solution to a problem.


Aman Rawal , Geek by profession, Deep interest in science Oct, 14 2016


Imagine you were playing a game of tic-tac-toe and I gave you a book with 5800 pages. Each page had one possible state of the game and the corresponding best move. Before each move you can look up the answer in the book. That is a simplified explanation of recursion.

Now imagine instead that each page of the book had strategies, patterns you can recognize that apply to many different situation. The book could be so much less than 5800 pages and would still be just as effective! That is basically modern machine learning, the model can generalize strategies.

Wth a game like chess and go there are way more than 5800 possible moves so it is very important we get that page count down, our computers can only remember so much!

Imagine you were playing a game of tic-tac-toe and I gave you a book with 5800 pages. Each page had one possible state of the game and the corresponding best move. Before each move you can look up the answer in the book. That is a simplified explanation of recursion. Now imagine instead that each pa


Himanshu Shekhar , Studying Computer Science in MIT Pune Oct, 14 2016


When one of the greatest chess players of the time, José Raúl Capablanca, was asked how many moves ahead he looked when playing a game. He replied "Only one, but it's always the right one." This is basically the difference between how deep neural networks differ from recursion and backtracking.

Backtracking algorithms work by searching through millions of different possibilities for what could happen next in the game, trying to find some way to force their opponent into losing. Deep neural nets don't do this. Instead they play like José Raúl Capablanca and don't do any searching at all. Instead, they look at the entire board and use sophisticated pattern matching to guess if it looks more like the kind of game that's likely to lead to a win vs. a loss. Often this pattern matching is based on a huge database of professional games, combined with a long pre-computation to fine-tune the patterns by having the computer play itself millions of times and seeing how often the neural net's guess is correct (and slightly modifying the neural net accordingly).

When one of the greatest chess players of the time, José Raúl Capablanca, was asked how many moves ahead he looked when playing a game. He replied "Only one, but it's always the right one." This is basically the difference between how deep neural networks differ from recursion and backtracking. Ba