TensorFlow is an open source software that provides libraries for numerical computation used for Machine Learning (ML) research. It is designed to be used easily. Python is the scripting language that interfaces the core part of the libraries written in C++. A complex ML code can be written with several lines in Python to run experiments while one can write codes in C++ to extend the existing functionalities of TensorFlow.

Google released TensorFlow on Nov. 10, 2015 (Mon) and many people will use it from the near future. It will become one of the de facto standards for machine learning research; at least, for deep learning research which is a sub-field of machine learning. I believe many people will add their own codes to TensorFlow.

I welcome Google’s decision to release TensorFlow and wish it grows and prospers. Curiosity urged me to install TensorFlow and play with it. But as of Nov. 10, 2015,  the binary installation does not work as smooth as I expected (like other well-made open source softwares). So I decided to share my experience with TensorFlow on this website. More to come.