Best Julia library for neural networks

Question

I have been using this library for basic neural network construction and analysis.

However, it does not have support for building multi-layered neural networks, etc.

So, I would like to know of any nice libraries for doing advanced neural networks and Deep Learning in Julia.

@itdxer Thank you for the link. Can you put that as an answer by elaborating about it? — Dawny33, Nov 19 '15 at 10:17

itdxer · Answer 1 · 2015-11-19T12:56:19.593

MXNet Julia Package - flexible and efficient deep learning in Julia

https://github.com/dmlc/MXNet.jl

Pros

Fast
Scales up to multi GPUs and distributed setting with auto parallelism.
Lightweight, memory efficient and portable to smart devices.
Automatic Differentiation

Cons

Doesn't have yet low level operations for algorithm implementation. But they are working on this issue (https://github.com/dmlc/mxnet/issues/586)

score 7 · Accepted Answer · answered Nov 19 '15 at 13:17

7

Mocha.jl - Mocha is a Deep Learning framework for Julia, inspired by the C++ framework Caffe.

Project with good documentation and examples. Can be run on CPU and GPU backend.

answered Nov 19 '15 at 13:17

Bartłomiej Twardowski

409
2
3

1

I think they stopped developing Mocha and MXNet is the way to go forward. See malmaud's comment here: https://github.com/pluskid/Mocha.jl/issues/157 – niczky12 Aug 01 '16 at 13:31
I've used Mocha for a while, it's got some issues and lacks a community, I concur that MXNet is where active development is. There's also a Julia wrapper for Tensorflow: https://github.com/malmaud/TensorFlow.jl (disclamer: I haven't used either, MXNet or the TF Julia Wrapper) – davidparks21 Oct 08 '16 at 22:19

score 5 · Answer 3 · answered May 25 '19 at 01:46

Just to add a more recent (2019) answer: Flux.

Flux is an elegant approach to machine learning. It's a 100% pure-Julia stack,
and provides lightweight abstractions on top of Julia's native GPU and
AD support. Flux makes the easy things easy while remaining fully hackable.

For example:

model = Chain(
  Dense(768, 128, σ),
  LSTM(128, 256),
  LSTM(256, 128),
  Dense(128, 10),
  softmax)

loss(x, y) = crossentropy(model(x), y)

Flux.train!(loss, data, ADAM(...))

score 3 · Answer 4 · edited Aug 05 '20 at 13:58

3

As of Oct 2016 there's also a Tensorflow wrapper for Julia.

edited Aug 05 '20 at 13:58

Zephyr

997
4
10
20

answered Oct 08 '16 at 22:22

davidparks21

423
4
17

score 1 · Answer 5 · edited Aug 05 '20 at 13:58

1

One newer library to look at as well is Knet.jl. It will do things like use GPUs under the hood.

edited Aug 05 '20 at 13:58

Zephyr

997
4
10
20

answered Mar 07 '17 at 20:15

Chris Rackauckas

111
3

Best Julia library for neural networks

5 Answers5