It is a machine-learning library using data flow graphs to build models. TensorFlow has been created for Deep Learning to let a user create a neural network architecture by himself (or herself, of course). Actually, tensors flow in the graph from node to node, thus making the name of the library sound logical. For some of you it may be interesting if there is any difference between TensorFlow and libraries like Theano, which also can make their own Deep Learning with multi-dimensional arrays and GPU.

Below there's the whole Gist page containing the full Python code. It has been developed and tested with Theano/GPU support, but it can easily work with CPU-only support. Any comment or suggestion is welcome!

This post is made up of a collection of 10 Github repositories consisting in part, or in whole, of IPython (Jupyter) Notebooks, focused on transferring data science and machine learning concepts. This warmup notebook is from postdoctoral researcher Randal Olson, who uses the common Python ecosystem data analysis/machine learning/data science stack to work with the Iris dataset. Aaron Masino has shared a series of very detailed, very technical machine learning IPython Notebook learning resources. From UC Boulder's Research Computing group, this older collection of notebooks (it's from way back in Fall 2013) covers a wide range of material, with an apparent focus on Linux command line-powered data management.