|
From: | Francesco Faccio |
Subject: | Re: Working on nnet package |
Date: | Sun, 1 Jan 2017 16:14:19 +0000 |
Julien Bect wrote:
Hi Julien, thank you very much for your detailed answer, I would really like to have a thorougly tested Matlab compatible nnet package in Octave. There are also some colleagues of mine which would be interested to contribute on this project from March/April and it would be nice to get them involved. I have already considered to use TensorFlow or Torch as external libraries, which both have a C++ interface, writing the most important functions as oct-files (I've already done something like this in my GSoC project). Moreover, starting from March, I will work on the development of the Deep Learning part of the package (documented here: [1][2]) and I will make full use of these libraries. At the moment I am trying to fix the most simple functions (the ones which do not require to be written as oct-file) and to add tests, then I will start linking libraries. Do you think it would be interesting for OF to keep Matlab compatibility and to use these libraries? Thank you, Francesco [1]https://it.mathworks.com/help/nnet/convolutional-neural-networks.html [2]https://it.mathworks.com/help/nnet/autoencoders.html |
[Prev in Thread] | Current Thread | [Next in Thread] |