There are some popular deep learning libraries used in research and commercial applications. Let's look at them individually here:

• TensorFlow: This is an open source software library for numerical computation using data flow graphs. The TensorFlow library (https://www.tensorflow.org/) is designed for machine intelligence and developed by the Google Brain team. The main aim of this library is to perform machine learning and deep neural network research. It can be used in a wide variety of other domains as well.
• Theano: Theano is an open source Python library (http://deeplearning.net/software/theano/) allowing us to streamline and assess mathematical expressions including multidimensional arrays proficiently. Theano was essentially created by the machine learning group at the Montreal University, Canada.

• Torch: Torch is a scientific computing framework with more support for machine learning algorithms with GPU as a priority. It's very efficient, being built on the scripting language LuaJIT and has an underlying C/CUDA implementation (http://torch.ch/).
• Caffe: Caffe (http://caffe.berkeleyvision.org/) is a deep learning library made with a focus on modularity, speed, and expression. It was developed by the Berkeley Vision and Learning Centre (BVLC).

The next section will help us to get started with TensorFlow.