[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: computer-go: Neural Nets: suggesting and evaluating



I have often been wondering about using much higher level inputs to the
NN. By doing a lot of tactical reading...
...
Is this a well-known approach, or have I stumbled upon a new idea? Any
experiences or even speculation on how it might work or fail?
I've mentioned it to people before, and it has always seemed obvious to me as well. However training times increase dramatically because of time spent doing tactical reading, and *then* training times increase dramatically because you are presenting something more complicated to the net and it is harder to learn it.

The 2nd issue is what I've been told from people who have done experiments with neural nets. No personal experience.

Darren