Question: TF & convnetjs for a JS tsumego solver

Hi Andrew,

Do you think it's the best approach to construct and train a simple DCNN in tensorflow and then run the trained NN with convnetjs in a JS app?

Basically, I'm writing a tsumego solver in JS and recently I've found a [paper](http://www.cs.cityu.edu.hk/~hwchun/research/PDF/Julian%20WONG%20-%20CCCT%202004%20a.pdf) that describes promising results in application of NNs to tsumego solving. I want to replicate that NN, train on my data, make a couple improvements and use in my solver.

TF is supposed to be very fast as it uses C++ back-end with state-of-the-art (I hope) matrix-related and other algorithms. However somewhere on stackoverflow people claimed that convnetjs is way faster despite it's in JS. I'm a newbie in machine learning (still completing the TF tutorial), hence asking.

Regards.

The issue mentions a JavaScript tsumego solver, TensorFlow, convnetjs, and a paper, but names no repository files, tests, or entry points. Start by clarifying the intended solver scope and whether the work belongs in this repository. Done would require an agreed implementation plan for training and running the neural network.

Written by the indexing model from the issue text.