Humans have always had a fundamental advantage over conventional computers: humans can learn from experience. However, a new generation of artificial intelligence algorithms (deep neural networks) is rapidly eliminating that advantage. Deep neural networks rely on adaptive algorithms to master a wide variety of tasks, including cancer diagnosis, object recognition, speech recognition, robotic control, and playing games such as chess, poker, backgammon and Go at super-human levels of performance.
In this richly illustrated book, a range of examples is used to explore the mathematics of neural networks, including perceptrons, backprop networks, Hopfield nets, Boltzmann machines, deep convolutional neural networks and reinforcement learning. Additionally, online computer programs give hands-on experience of neural networks in action, and PowerPoint slides provide support for teaching. Written in an informal style, with a comprehensive glossary and tutorial appendices, this is an ideal introduction to the algorithmic engines that power modern artificial intelligence.

Available in Spring 2019.

ISBN: 9780993367977.

To receive news regarding the publication of this book, please subscribe to the mailing list below (email addresses remain confidential)