Theano Library

Context:
- It can be used as a Deep Learning Library.
- It can (typically) be slow because it is Python-based.
- It can integrate with Numpy.
- It can make use of a CUDA GPU Platform or (soon) an OpenCL Platform [1].
Example(s):
- Theano v1.0 (final release).
- …
Counter-Example(s):
- TensorFlow.
- Torch Library.
- Deeplearning4j.
- Keras.
- MXNet.
- sklearn.neural_networks.
- pylearn, and numpy.
- cuda-convnet a C++-based convolutional/feed-forward neural networks.
- deepnet.
- CUV NN library.
- nnForge Library, a C++ library for training convolutional fully-connected neural networks.
- Caffe Framework.
See: numpy, Automatic Differentiation, CUDA GPU Platform, Keras Library.

References

https://groups.google.com/forum/#!topic/theano-users/7Poq8BZutbY
- QUOTE: After almost ten years of development, we have the regret to announce that we will put an end to our Theano development after the 1.0 release, which is due in the next few weeks.

Software	Creator	Software licenseTemplate:Efn	Open source	Platform	Written in	Interface	OpenMP support	OpenCL support	CUDA support	Automatic differentiation^[1]	Has pretrained models	Recurrent nets	Convolutional nets	RBM/DBNs	Parallel execution (multi node)
Theano	Université de Montréal	BSD license	Yes	Cross-platform	Python	Python	Yes	Template:Depends	Yes	Yes^[2]^[3]	Template:Depends	Yes	Yes	Yes	Yes^[4]

http://github.com/ASIDataScience/training-neural-networks-notebook/blob/master/Training-Neural-Networks-Theano.ipynb
- QUOTE: Theano allows us to write relatively concise code that follows the structure of the underlying maths. ...
  import theano ; import theano.tensor ;

http://en.wikipedia.org/wiki/Automatic_differentiation#Software
- Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays both on CPU and GPU efficiently.

http://deeplearning.net/software/theano/
- Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Theano features:
  - tight integration with NumPy – Use numpy.ndarray in Theano-compiled functions.
  - transparent use of a GPU – Perform data-intensive calculations up to 140x faster than with CPU.(float32 only)
  - efficient symbolic differentiation – Theano does your derivatives for function with one or many inputs.

http://deeplearning.net/software/theano/introduction.html#introduction
- Theano is a Python library that lets you to define, optimize, and evaluate mathematical expressions, especially ones with multi-dimensional arrays (numpy.ndarray). Using Theano it is possible to attain speeds rivaling hand-crafted C implementations for problems involving large amounts of data. It can also surpass C on a CPU by many orders of magnitude by taking advantage of recent GPUs.
  Theano combines aspects of a computer algebra system (CAS) with aspects of an optimizing compiler. It can also generate customized C code for many mathematical operations. This combination of CAS with optimizing compilation is particularly useful for tasks in which complicated mathematical expressions are evaluated repeatedly and evaluation speed is critical. For situations where many different expressions are each evaluated once Theano can minimize the amount of compilation/analysis overhead, but still provide symbolic features such as automatic differentiation.