You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

Houshalter comments on AlphaGo versus Lee Sedol - Less Wrong Discussion

17 Post author: gjm 09 March 2016 12:22PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (183)

You are viewing a single comment's thread. Show more comments above.

Comment author: Houshalter 10 March 2016 04:42:45AM 2 points [-]

Yes binary neural networks are super interesting because they can be made much more compact in hardware than floating point ops. However there isn't much (theoretical) advantage otherwise. Anything a circuit can do, an NN can do, and vice versa.

A circuit size penalty is already a very common technique. It's called weight decay, where the synapses are encouraged to be as close to zero as possible. A synapse of 0 is the same as it not being there, which means the neural net parameters requires less information to specify.