This book systematically narrates the fundamentals, methods, and recent advances of evolutionary deep neural architecture search chapter by chapter. This will provide the target readers with sufficient details learning from scratch. In particular, the method parts are devoted to the architecture search of unsupervised and supervised deep neural networks. The people, who would like to use deep neural networks but have no/limited expertise in manually designing the optimal deep architectures, will be the main audience. This may include the researchers who focus on developing novel evolutionary deep architecture search methods for general tasks, the students who would like to study the knowledge related to evolutionary deep neural architecture search and perform related research in the future, and the practitioners from the fields of computer vision, natural language processing, and others where the deep neural networks have been successfully and largely used in their respective fields.

Introduces the fundamentals and up-to-date methods of evolutionary deep neural architecture search Provides the target readers with sufficient details learning from scratch Inspires the students to develop more effective and efficient EDNAS methods

Inhalt
Part I: Fundamentals and Backgrounds.- Evolutionary Computation.- Deep Neural Networks.- Part II: Evolutionary Deep Neural Architecture Search for Unsupervised DNNs.- Architecture Design for Stacked AEs and DBNs.- Architecture Design for Convolutional Auto-Encoders.- Architecture Design for Variational Auto-Encoders.- Part III: Evolutionary Deep Neural Architecture Search for Supervised DNNs.- Architecture Design for Plain CNNs.- Architecture Design for RBs and DBs Based CNNs.- Architecture Design for Skip-Connection Based CNNs.- Hybrid GA and PSO for Architecture Design.- Internet Protocol Based Architecture Design.- Dierential Evolution for Architecture Design.- Architecture Design for Analyzing Hyperspectral Images.- Part IV: Recent Advances in Evolutionary Deep Neural Architecture Search.- Encoding Space Based on Directed Acyclic Graphs.- End-to-End Performance Predictors.- Deep Neural Architecture Pruning.- Deep Neural Architecture Compression.- Distribution Training Framework for Architecture Design.