Chapter 10

Deep Learning

Abstract

Deep learning is one of the fastest growing areas of data science. Deep learning refers to a class of algorithms which are based on artificial neural networks optimized to work with unstructured data such as images, voice, videos and text. While the techniques of deep learning date back to the mid-80s, their true potential has been realized only in the last 5 years or so. This chapter covers some of the early history, develops a conceptual framework for introducing deep learning in general. It also describes a practical implementation of deep learning.

Keywords

Deep learning; convolutional neural network; gradient descent; Tensorflow; Keras; recurrent neural network; activation function

To get a deep-learning system ...

Get Data Science, 2nd Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.