Theano - Ep. 17 (Deep Learning SIMPLIFIED)

Theano is a Python library that defines a set of mathematical functions for building deep nets. Nets that use these functions as their building blocks will be highly optimized for training.

Deep Learning TV on

The core feature of Theano is the use of vectors and matrices for all of its functions. Vectorized code runs quickly since multiple values can be processed in parallel. Since Deep Nets require large amounts of computation throughout the training process, vectorization is a highly-recommended feature. Theano is multi-threaded with GPU support, so deep nets can be trained on just a single machine within a reasonable amount of time.

To use Theano for Deep Learning, you must code every aspect of a deep net including the layers, the nodes, the activation, and the training rate. However, all the functions that run your code will be vectorized, resulting in an efficient implementation. Many software libraries extend Theano, making it easier to use in your projects. The Blocks library helps by parameterizing Theano functions. The Lasagne library allows you to specify hyper-parameters in order to build a net layer by layer. Niche libraries like Passage help implement recurrent nets for text analysis.

Do you have experience coding neural nets with the Theano library? Please comment and share your thoughts.

Credits
Nickey Pickorita (YouTube art) -
Isabel Descutner (Voice) -
Dan Partynski (Copy Editing) -
Marek Scibior (Prezi creator, Illustrator) -
Jagannath Rajagopal (Creator, Producer and Director) -

[DeepLearningTV]

As a beginner to coding deep nets, you probably wanna consider using Theano. Enjoy :-)

[Existentialkev]

If you have to code a deep net yourself in all of its aspects... is it really that beginner friendly?

[DeepLearningTV]

Next one comes out Jan 14, 2016 and is on the Java library DeepLearning4j.

[parampopat]

But since we are scripting the functions on our own for each aspect like the neuron, optimizer, etc., can't we parallelize model to train over mulit-GPUs?

[GopalSharma-sfzz]

What is the alternative of Theano, which also has python implementation and can support distributed multi node training? Does TensorFlow fits the above profile?

[theanotaylor]

Omg my name is theano for crying out loud😎😎😎😎

[manasi]

Hello,
I have been working on Google's paper FaceNet: A Unified Embedding for Face Recognition and Clustering. I am trying to build a convolutional model for face recognition using theano. Also I am trying to build my Op for triplet loss layer as mentioned in this paper .
Can I get any substantial help in this regard ?

[kikirizki]

is theano has lower level of abstraction than tensorflow?