Offering a variety of connectionist models that are representative of the state-of-the-art, this textbook provides a succinct, accessible, and interesting first introduction to deep learning. The work takes a user-friendly approach to examining today's top algorithms and architectures, walking readers through the arithmetic behind each concept as it is introduced. Convolutional networks, long short-term memories, word2vec, random bit networks, decision-based networks, neural Turing machines, memory networks, autoencoders, and more are all discussed. The book is filled with functional Python code examples, and the code is also available for download on a companion website.