Re: [Computer-go] Exploiting Cyclic Symmetry in Convolutional Neural Networks

2018-02-28 Thread Steven Clark
See also: Oriented Response Networks https://arxiv.org/abs/1701.01833 On Wed, Feb 28, 2018 at 11:40 AM, Jonathan Roy wrote: > I'm curious if anyone has applied this idea in their Go software, and what > results you obtained? It is a way to make rotations (and transpositions > with more effort) g

Re: [Computer-go] Exploiting Cyclic Symmetry in Convolutional Neural Networks

2018-02-28 Thread Jonathan Roy
> > To follow up on the paper I listed earlier I just found this link with a > long list of related papers: > > http://www.arxiv-sanity.com/1705.08623v1 > > Many from 2016-2018 and all dealing with neural networks and ways to solve > rotation. Deep Rotation Equivariant Network ( > http://arxiv.org/

[Computer-go] Exploiting Cyclic Symmetry in Convolutional Neural Networks

2018-02-28 Thread Jonathan Roy
I'm curious if anyone has applied this idea in their Go software, and what results you obtained? It is a way to make rotations (and transpositions with more effort) go away as an issue, regardless of the way you input the board you'd get the same result back out. Short summary from the paper ( http