TensorFlow – Not Just for Deep Learning

One time when I was illustrating the code base and architecture of TensorFlow to my friends, they were quite surprised by how much more code was introduced since TensorFlow’s first open-source release. They were only expecting several popular types of deep learning algorithms from the code base as heard from other people and social media. Yet, TensorFlow is not just for deep learning. It provides a great variety of building blocks for general numerical computation and machine learning. In this blog post, I will introduce the wide range of general machine learning algorithms and their building blocks provided by TensorFlow in tf.contrib. Note that many of the modules in tf.contrib will be moved to the main TensorFlow module once their interfaces are more stable. High-level TF.Learn Estimators TF.Learn is a…


Link to Full Article: TensorFlow – Not Just for Deep Learning