theano

I used Theano, and figuring out how to translate my dataset into a format digestible by Theano took another chunk of time.

I think it's main advantage is that it uses theano under the hood but the user does not need to know theano at all.

You should know your way around Torch, Theano - and basically be able to start programming from day one.

The simplest example is the RNN-RBM (restricted boltzmann machine) from the Theano deep learning tutorials [1].

But it's using Theano under the hood, which is well optimized and should be very competitive with Torch and Caffe.

Both Theano and Caffe (dont know about Torch) will already use cuDNN if its installed.

Can you suggest any good video explanation about NN but with some code with Python but using an actual NN library (like theano)?

Once you get that you should move to more mature implementations, like Theano or Torch to get the full potential of neutral nets without worrying about implementation.

After stumbling upon Keras, I was up in running in minutes, and the huge performance boost of Theano allowed me to actually finish on time.

I have experimented with FFT convolutions (the Theano implementation for this is based on my code), but they are only really beneficial with large filters, and the current trend is towards convnets with very small filters (1x1, 2x2 or 3x3).

There are also some great lectures from Aaron Courville from the Representation Learning class that just finished here at UdeM [5] If you want to do this for real (not self teaching RNN backprop on toy examples) tool-wise you generally go with either Theano (my preference) or Torch - implementing the backwards path for these (and verifying gradients are correct) is not pretty.

There is a lackluster theano feature which allows you to print a flowchart figure for the "computation graph" corresponding to the symbolic representation of your model.

We're already seeing that with integrated, "soldered-on" graphics cards, and with frameworks like OpenCL, and higher-level abstractions like Theano, Torch7, etc.

Theano does it almost for free, and Torch can do it at the module level.

Once I had my data in the proper format for Theano, it came down to basically playing with how I presented my initial data to Theano, and then tweaking my gradient.

We use a wide range of tools and languages, including Python (Theano, Pandas/Numpy/etc, Flask), Meteor, CoffeeScript, and C++ (Caffe).