This bookis a survey and analysis of how deep learning can be used to generate musicalcontent. The authors offer a comprehensive presentation of the foundations ofdeep learningtechniques for music generation. They also develop a conceptualframework used to classify and analyze various types of architecture, encodingmodels, generation strategies, and ways tocontrol the generation. The five dimensionsof this framework are: objective (the kind of musical content to be generated, e.g.,melody, accompaniment); representation (the musicalelements to be considered andhow to encode them, e.g., chord, silence, piano roll, one-hot encoding);architecture (the structure organizing neurons, their connexions, and the flowof theiractivations, e.g., feedforward, recurrent, variational autoencoder);challenge (the desired properties and issues, e.g., variability,incrementality, adaptability); and strategy (the way to modeland control theprocess of generation, e.g., single-step feedforward, iterative feedforward,decoder feedforward, sampling). To illustrate the possible design decisions andto allowcomparison and correlation analysis they analyze and classify morethan 40 systems, and they discuss important open challenges such as interactivity,originality, and structure.

The authorshave extensive knowledge and experience in all related research, technical,performance, and business aspects. The book is suitable for students,practitioners, andresearchersin the artificial intelligence, machine learning, and music creation domains.The reader does not require any prior knowledge about artificial neuralnetworks, deep learning, orcomputer music. The text is fully supported with acomprehensive table of acronyms, bibliography, glossary, and index, andsupplementary material is available from the authors' website.