Re: [Computer-go] Creating the playout NN

> > The purpose is to see if there is some sort of "simplification" available > to the emerged complex functions encoded in the weights. It is a typical > reductionist strategy, especially where there is an attempt to converge on > human conceptualization. > > That's an interesting way to look at

Re: [Computer-go] Creating the playout NN

> > BTW, by improvement, I don't mean higher Go playing skill...I mean > appearing close to the same level of Go playing skill _per_ _move_ with far > less computational cost. It's the total game outcomes that will fall. > > For the playouts, you always need a relatively inexpensive computation.

Re: [Computer-go] Creating the playout NN

BTW, by improvement, I don't mean higher Go playing skill...I mean appearing close to the same level of Go playing skill _per_ _move_ with far less computational cost. It's the total game outcomes that will fall. On Sun, Jun 12, 2016 at 3:55 PM, Jim O'Flaherty wrote:

Re: [Computer-go] Creating the playout NN

The purpose is to see if there is some sort of "simplification" available to the emerged complex functions encoded in the weights. It is a typical reductionist strategy, especially where there is an attempt to converge on human conceptualization. Given the complexity of the nuances in Go, my

Re: [Computer-go] Creating the playout NN

I don't remember the content of the paper and currently can't look at the PDF, but one possible explanation could be that a simple model trained directly maybe regularizes differently from one trained on the best-fit pre-smoothed output of a deeper net. The second could perhaps offer better local

Re: [Computer-go] Creating the playout NN

I don't understand the point of using the deeper network to train the shallower one. If you had enough data to be able to train a model with many parameters, you have enough to train a model with fewer parameters. Álvaro. On Sun, Jun 12, 2016 at 5:52 AM, Michael Markefka <

Re: [Computer-go] Creating the playout NN

Might be worthwhile to try the faster, shallower policy network as a MCTS replacement if it were fast enough to support enough breadth. Could cut down on some of the scoring variations that confuse rather than inform the score expectation. On Sun, Jun 12, 2016 at 10:56 AM, Stefan Kaitschick

Re: [Computer-go] Creating the playout NN

I don't know how the added training compares to direct training of the shallow network. It's prob. not so important, because both should be much faster than the training of the deep NN. Accuracy should be slightly improved. Together, that might not justify the effort. But I think the fact that

Re: [Computer-go] Creating the playout NN

Would the expected improvement be reduced training time or improved accuracy? 2016-06-11 23:06 GMT+03:00 Stefan Kaitschick : > If I understood it right, the playout NN in AlphaGo was created by using > the same training set as the one used for the large NN that is

[Computer-go] Creating the playout NN

If I understood it right, the playout NN in AlphaGo was created by using the same training set as the one used for the large NN that is used in the tree. There would be an alternative though. I don't know if this is the best source, but here is one example: https://arxiv.org/pdf/1312.6184.pdf The