We’re rewarding the question askers & reputations are being recalculated! Read more.
32

I wrote a simple python script to draw convnet, with adjustable parameters. https://github.com/gwding/draw_convnet It might be useful to you, if you just need some simple/non-fancy illustration. It copies the style of Figure 2 in "gradient based learning applied to document recognition"


12

I wrote an in-browser tool for this as well: NN-SVG and you can find the source here. Choose from FCNN layout, LeNet layout, and AlexNet layout.


5

I wrote an in-browser tool for this: NN-SVG. Choose from FCNN layout, LeNet layout, and AlexNet layout.


4

Grant Sanderson a.k.a. 3Blue1Brown writes his own code to produce the figures he presents in his videos. The code is available at https://github.com/3b1b/manim and you may find the code for the neural network figures in https://github.com/3b1b/manim/tree/master/old_projects/nn Also: How to draw Deep learning network architecture diagrams?


3

You can use Caffe: open source (BSD 2-Clause license) gratis Easy to compile on Linux/OS X, harder on Windows GPU support for Nvidia on CPU, makes use of multithreading use the backpropagation algorithm allows the user to define neural network using config files MLP, CNN but no RNN yet written in C++ but Python and Matlab binds available FYI: Script to ...


2

There are no plain Theano setups just because application of RNN to speech is not trivial, you need to have a good estimation before training to make the whole system converge. CTC implementation for speech is usually based on Kaldi speech recognition toolkit which is used to setup the whole thing with speech specifics. You can find details here: Theano-...


2

It sounds like you should be looking into Gambit which is a GNU licensed package for exactly that sort of thing: Open Source - GNU GPL Licence Cross Platform Windows, Mac & Linux GUI for exploring strategies & outcomes Python API for implementing complex games, etc. Command-line tools gambit-enumpure: Enumerate pure-strategy equilibria of a game ...


2

This is great: https://github.com/HarisIqbal88/PlotNeuralNet. Solves my problem well, and is written in python/tex.


2

My goto for any natural language work is NLTK which in its own words is: NLTK is a leading platform for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, ...


2

You could use the "Network Import Example" Model from Netlogo and customize it with code from the "Network Example" (which shows an animated graph with links flipping around). Both Models are present in the Models Library (= preinstalled). Maybe its not your use-case and maybe it's too much effort to learn the new programming language. Maybe you need to ...


1

The Visual Computing department at UCL have published their work in this field. A github repository containing usable code can be found here: https://github.com/thaines/helit/tree/master/handwriting


1

If it is ok for you to use a Microsoft/.NET solution have a look at CNTK (Microsoft Cognitive Toolkit). https://docs.microsoft.com/en-us/cognitive-toolkit/ The Microsoft Cognitive Toolkit - CNTK - is a unified deep-learning toolkit by Microsoft. ... CNTK can be included as a library in your Python, C#, or C++ programs, or used as a standalone machine ...


1

I would suggest taking a look at SciKit learn - it is Python rather than Java but has a very permissive, (BSD), licence and is actively used, developed and supported. It is fully open source and free.


1

I am not familiar with Deep Belief Networks, but it looks like the word has evolved a little since this question was asked, and I found three alternatives are more or less relevant answers: In Matlab: See DeepLearnToolbox In Java: See Deeplearning4j or H20 Deep Learning See Looking for a convenient way to call Java from C++ for bridging the gap from C++ to ...


1

You can use the Python package theanets: open source (MIT License) gratis it's a wrapper around Theano (the latter can use your GPU if Nvidia, AMD is not fully supported yet). on CPU, does not make use of multithreading Easy to compile on Linux/OS X, harder on Windows MLP, RNN The following code shows how easy it is to specify an ANN and train it: import ...


Only top voted, non community-wiki answers of a minimum length are eligible