Until recently, human brains had one major advantage over computers: they can learn. However, the emergence of a new generation of artificial intelligence algorithms (deep learning artificial neural networks) is rapidly eliminating that advantage. Deep learning networks rely on adaptive algorithms to master a wide variety of tasks, including reading hand-writing, cancer diagnosis, speech recognition, robotic control, face recognition, and playing games such as poker and Go at super-human levels of performance. In this richly illustrated book, a wide range of examples is used to explore the mathematics of artificial neural networks, from perceptrons, multi-layer networks, Boltzmann machines to deep belief networks. Written in an informal style, this is an ideal introduction to the algorithmic engines that underpin modern artificial intelligence.

Available in late 2018.

ISBN: 9780993367977.

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