Re: [Computer-go] (no subject)

On 01.04.2016 02:22, djhbrown . wrote: kogo is great for corner openings Kogo contains many mistakes. Too many kyus got their hands on it. It would be better to spend 3+ weeks using kombilo on GoGoD and create a new joseki tree. A summary of such an effort (with some interesting,

Re: [Computer-go] (no subject)

on the subject of tools for learning josekis, i would love to have to the help of a computerised assistant who could show me a flip-through "photo album" of how alternative paths in a joseki end up, without having to plod along the paths (which to me is a dark and mysterious tree of paths in a

Re: [Computer-go] new challenge for Go programmers

Nice On Mar 31, 2016 7:48 AM, "Álvaro Begué" wrote: > A very simple-minded way of trying to identify what a particular neuron in > the upper layers is doing is to find the 50 positions in the database that > make it produce the highest activation values. If the neuron is

Re: [Computer-go] "English Explanations" based on Neural Networks

It all comes down to having a reasonable way to search the MCTS’s tree. An elegant tool would be wonderful, but even something basic would allow a determined person to find interesting things. When I was debugging SlugGo, which had a tree as wide as 24 and as deep as 10, with nothing other than

Re: [Computer-go] new challenge for Go programmers

On 31/03/2016, "Ingo Althöfer" <3-hirn-ver...@gmx.de> wrote: > somehow he went into a > "strange loop", and in the end he was asked to stop posting. asked by the very person i was trying to help! That was the last straw. Ironically, whilst i was openly trying to help all montes, not just

Re: [Computer-go] "English Explanations" based on Neural Networks

Major changes in the evaluation probability could likely have a horizon of a few moves behind that might be interesting to more closely evaluate. With a small window like that, a deeper/more exhaustive search might work. s. On Mar 31, 2016 10:21 AM, "Petr Baudis" wrote: > On Thu,

Re: [Computer-go] "English Explanations" based on Neural Networks

Petr, You know, just exploring this conversation is motivating to me, even if I am still seeing it as huge risk with small payoff. I like your line of thinking in that from a top down approach, we start simple and just push it as far as it can go, acknowledging we won't likely get anywhere near

Re: [Computer-go] "English Explanations" based on Neural Networks

On Thu, Mar 31, 2016 at 08:51:30AM -0500, Jim O'Flaherty wrote: > What I was addressing was more around what Robert Jasiek is describing in > his joseki books and other materials he's produced. And it is exactly why I > think the "explanation of the suggested moves" requires a much deeper > baking

Re: [Computer-go] "English Explanations" based on Neural Networks

Petr suggests "caption Go positions based on game commentary" Without doubt, there has to be a lot of mileage in looking for a way for a machine to learn from expert commentaries. i see a difference between labelling a cat in a photo and labelling a stone configuration in a picture of a board,

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

no On Thu, Mar 31, 2016 at 8:33 AM, Lucas, Simon M wrote: > Thanks Ryan, > > Nice paper – did you follow up on any of the future work? > > Simon > > > > From: Computer-go on behalf of Ryan > Hayward > Reply-To:

Re: [Computer-go] (no subject)

On 31.03.2016 16:54, Bill Whig wrote: Wouldn't you agree that a lot of people (most?) might might advance more swiftly > with move suggestions rather than text that they have to work through like a textbook? I say the opposite. Move suggestions without any additional information are

Re: [Computer-go] new challenge for Go programmers

A very simple-minded way of trying to identify what a particular neuron in the upper layers is doing is to find the 50 positions in the database that make it produce the highest activation values. If the neuron is in one of the convolutional layers, you get a full 19x19 image of activation values,

[Computer-go] (no subject)

Message: 1 Date: Thu, 31 Mar 2016 14:33:39 +0200 From: Robert Jasiek To: computer-go@computer-go.org Subject: Re: [Computer-go] new challenge for Go programmers Message-ID: <56fd1923.4080...@snafu.de> Content-Type: text/plain; charset=UTF-8; format=flowed On 31.03.2016 13:43,

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

Thanks Ryan, Nice paper – did you follow up on any of the future work? Simon From: Computer-go > on behalf of Ryan Hayward > Reply-To:

Re: [Computer-go] new challenge for Go programmers

Then again DNNs also manage feature extraction on unlabeled data with increasing levels of abstraction towards upper layers. Perhaps one could apply such a specifically trained DNN to artificial board situations that emphasize specific concepts and examine the network's activation, trying to map

Re: [Computer-go] new challenge for Go programmers

Ingo, That's precisely what has my knickers in a twist regarding djhbrown; his prior behavior. I'm with you in that I hope that he better manages his participation and uses list feedback to spend a little more time filtering what his "creativity" so it fits closer to the listening of this

Re: [Computer-go] new challenge for Go programmers

Robert, This is exactly why I think the "explanation of the suggested moves" requires a much deeper baking into the participating ANN's (bottom up approach). And given what I have read thus far, I am still seeing the risk extraordinarily high and the payoff exceedingly low, outside an academic

Re: [Computer-go] new challenge for Go programmers

Message: 3 Date: Thu, 31 Mar 2016 08:35:51 +0200 From: Robert Jasiek To: computer-go@computer-go.org Subject: Re: [Computer-go] new challenge for Go programmers Message-ID: <56fcc547@snafu.de> Content-Type: text/plain; charset=UTF-8; format=flowed On 31.03.2016 03:52, Bill

[Computer-go] "English Explanations" based on Neural Networks

On Wed, Mar 30, 2016 at 09:58:48AM -0500, Jim O'Flaherty wrote: > My own study says that we cannot top down include "English explanations" of > how the ANNs (Artificial Neural Networks, of which DCNN is just one type) > arrive a conclusions. I don't think that's obvious at all. My current avenue

Re: [Computer-go] new challenge for Go programmers

Yes, I recall that earlier episode. I would be happy to have a better relationship going forward. I wrote some explanation generators for Scrabble and Chess AI, but these were much simpler systems that I could break apart. E.g., the Chess engine would play two moves out until a "quiet"

Re: [Computer-go] new challenge for Go programmers

Hello all, "Brian Sheppard" wrote: > ... This is out of line, IMO. Djhbrown asked a sensible question that has > valuable intentions. I would like to see responsible, thoughtful, and > constructive replies. there is a natural explanation why some people here react allergic

Re: [Computer-go] new challenge for Go programmers

On 31.03.2016 03:52, Bill Whig wrote: If the program would merely output 3-5 suggested positions, that would probably suffice. Even an advanced beginner, such as myself, could I believe, understand why they are good choices. Just having the "short list" would probably be quite an educational

Re: [Computer-go] new challenge for Go programmers

"Similar to Neuro-Science, where reverse engineering methods like fMRI reveal structure in brain activity, we demonstrated how to describe the agent’s policy with simple logic rules by processing the network’s neural activity. This is important since often humans can understand the optimal policy

Re: [Computer-go] new challenge for Go programmers

this is also interesting, to visualize "how the NN thinks" http://blog.acolyer.org/2016/03/02/graying-the-black-box-understanding-dqns/ On Wed, Mar 30, 2016 at 10:38 PM, Ben wrote: > It would be very interesting to see what these go playing neural networks > dream