Re: [Computer-go] AlphaGo Zero

On Wed, Oct 18, 2017 at 04:29:47PM -0700, David Doshay wrote: > I saw my first AlphaGo Zero joke today: > > After a few more months of self-play the games might look like this: > > AlphaGo Zero Black - move 1 > AlphaGo Zero White - resigns ...which is exactly what my quick attempt to reproduce

Re: [Computer-go] AlphaGo Zero

I have two questions. 2017 Jan, Master , defeat 60 pros in a row. 2017 May, Master?, defeat Ke Jie 3-0. Master is Zero method with rollout. Zero is Zero method without rollout. Did AlphaGo that played with Ke Jie use rollout? Is Zero with rollout stronger than Zero without rollout? Thanks,

Re: [Computer-go] AlphaGo Zero

This is a quick check of my understanding of the network architecture. Let's count the number of parameters in the model: * convolutional block: (17*9+1)*256 + 2*256 [ 17 = number of input channels 9 = size of the 3x3 convolution window 1 = bias (I am not sure this is needed if you are

Re: [Computer-go] AlphaGo Zero

On 18-10-17 19:50, cazen...@ai.univ-paris8.fr wrote: > > https://deepmind.com/blog/ > > http://www.nature.com/nature/index.html Another interesting tidbit: The inputs don't contain a reliable board edge. The "white to move" plane contains it, but only when white is to move. So until AG Zero

Re: [Computer-go] AlphaGo Zero

On Thu, Oct 19, 2017 at 11:04 AM, Hiroshi Yamashita wrote: > I have two questions. > > 2017 Jan, Master , defeat 60 pros in a row. > 2017 May, Master?, defeat Ke Jie 3-0. > > Master is Zero method with rollout. > Zero is Zero method without rollout. > > Did AlphaGo that

Re: [Computer-go] agz -- meditations

Well, if you have both, why not use both :) On Thu, Oct 19, 2017 at 11:51 AM Richard Lorentz wrote: > An interesting juxtaposition. > > Silver said "algorithms matter much more than ... computing". > > Hassabis estimated they used US$25 million of hardware. >

[Computer-go] agz -- meditations

An interesting juxtaposition. Silver said "algorithms matter much more than ... computing". Hassabis estimated they used US$25 million of hardware. ___ Computer-go mailing list Computer-go@computer-go.org

Re: [Computer-go] AlphaGo Zero

What shall I say? Really impressive. My congratulations to the DeepMind team! > https://deepmind.com/blog/ > http://www.nature.com/nature/index.html * Would the same approach also work for integral komi values (with the possibility of draws)? If so, what would the likely correct komi for 19x19

Re: [Computer-go] AlphaGo Zero

Yes, it seems really odd that they didn't add a plane of all ones. The "heads" have weights that depend on the location of the board, but all the other layers can't tell the difference between a lonely stone at (1,1) and one at (3,3). In my own experiments (trying to predict human moves) I found

Re: [Computer-go] AlphaGo Zero

The order of magnitude matches my parameter numbers. (My attempt to reproduce a simplified version of this is currently evolving at https://github.com/pasky/michi/tree/nnet but the code is a mess right now.) On Thu, Oct 19, 2017 at 07:23:31AM -0400, Álvaro Begué wrote: > This is a quick check

Re: [Computer-go] AlphaGo Zero

I would like to know how much handicap the Master version needs against the Zero version. It could be less than black without komi or more than 3 stones. Handicap differences cannot be deduced from regular Elo rating differences, because it varies depending on skill (a handicap stone is more

Re: [Computer-go] agz -- meditations

Sure, both hardware and software / algorithms are needed... but which gets you the bigger ROI? { Just a rhetorical question, I know it is not linear and not a simple question... but in general, I can see David Silver's (& Richard Lorentz / Demis Hassabis' counter) point }. May you live in sente,

Re: [Computer-go] agz -- meditations

Cost reduction in IC has reached or is reaching its limits. Intels 5n techk is not really a 5n and 5n is not really reachable. Not at least without some seriously new physics and even then there will be hard limits like quantum un--certainty. This particular chip may get cheaper if it is ever done

Re: [Computer-go] AlphaGo Zero

So I am reading that residual networks are simply better than normal convolutional networks. There is a detailed write-up here: https://blog.waya.ai/deep-residual-learning-9610bb62c355 Summary: the residual network has a fixed connection that adds (with no scaling) the output of the previous

Re: [Computer-go] AlphaGo Zero

Yes, residual networks are awesome! I learned about them at ICML 2016 ( http://kaiminghe.com/icml16tutorial/index.html). Kaiming He's exposition was fantastically clear. I used them in my own attempts at training neural networks for move prediction. It's fairly easy to train something with 20

Re: [Computer-go] agz -- meditations

On 19.10.2017 20:13, Richard Lorentz wrote: Silver said "algorithms matter much more than ... computing". Hassabis estimated they used US$25 million of hardware. Today, it seems 4 TPU cost US$25 million. In 5 or 10 years, every computer might have its 4-TPU-chip costing $250, if not $25. At

Re: [Computer-go] AlphaGo Zero

So there is a superstrong neural net. 1) Where is the semantic translation of the neural net to human theory knowledge? 2) Where is the analysis of the neural net's errors in decision-making? 3) Where is the world-wide discussion preventing a combination of AI and (nano-)robots, which