Thanks David! You’re right, it should be possible to somehow read out that prototxt file. I’ll see how that goes for me. :) The rest of your info is still a bit mysterious for me. But I will figure it out eventually.
Urban On Fri, May 20, 2016 at 9:49 PM, David Fotland <[email protected]> wrote: > The alphaGo network is detailed in their paper. They have about 50 binary > inputs, one layer of 5x5 convolutional filters, and about 12 layers of 3x3 > convolutional filters. Detlef’s net is specified in the prototxt file he > published here. It’s wider and deeper, but with fewer inputs. > > > > The current popular approach is a to use 5x5 or 7x7 filters in the first > layers, and 3x3 filters in higher layers. The topmost layer is special, > typically a 1x1 convolutional filter. AlphaGo uses position dependent > biases. RelU seems to work well, and pooling is not used (for obvious > reasons). > > > > In my experiments it is essential to have the first layer filters larger > than 3x3. In higher layers 3x3 seems to work fine. > > > > Hope this helps. > > > > David > > > > *From:* Computer-go [mailto:[email protected]] *On > Behalf Of *Urban Hafner > *Sent:* Friday, May 20, 2016 4:47 AM > *To:* [email protected] > *Subject:* [Computer-go] Commonly used neural network architectures > > > > Hey there, > > > > just like everyone else I’m currently looking into neural networks for my > go program. ;) Apart from the AlphaGo paper where I can I find information > about network architecture? There’s the network from April 2015 from Detlef > (http://computer-go.org/pipermail/computer-go/2015-April/007573.html) but > I don’t know enough about caffe to figure out the architecture. Basically, > I more interested in understanding how to build a network myself than just > using a pre-trained network. > > > > Cheers, > > > > Urban > > -- > > Blog: http://bettong.net/ > > Twitter: https://twitter.com/ujh > > Homepage: http://www.urbanhafner.com/ > > _______________________________________________ > Computer-go mailing list > [email protected] > http://computer-go.org/mailman/listinfo/computer-go > -- Blog: http://bettong.net/ Twitter: https://twitter.com/ujh Homepage: http://www.urbanhafner.com/
_______________________________________________ Computer-go mailing list [email protected] http://computer-go.org/mailman/listinfo/computer-go
