The book presents a comprehensive study of scientific creativity through two complementary modalities: biological and computational. The biological modality examines the neural basis of creativity through brain connectivity analysis, focusing on spatial ability, analogical reasoning, convergent thinking, cognitive flexibility, and aesthetic sensibility. It employs graph networks, attention mechanisms, type-2 fuzzy inference, and capsule-based deep learning to assess creative potential. The computational modality explores the artificial synthesis of creativity using diversity-aware search techniques, including best-first search, and generative models such as Generative Adversarial Networks (GANs). The book is primarily intended for scientists/researchers pursuing research in artificial intelligence and cognitive sciences. It is also useful for general readers/hobbyists in computer science and electronics engineering, for its useful and interesting contents on scientific creativity.
This book presents a comprehensive study of scientific creativity through two complementary modalities: biological and computational. The biological modality examines the neural basis of creativity through brain connectivity analysis, focusing on spatial ability, analogical reasoning, convergent thinking, cognitive flexibility, and aesthetic sensibility. It employs graph networks, attention mechanisms, type-2 fuzzy inference, and capsule-based deep learning to assess creative potential. The computational modality explores the artificial synthesis of creativity using diversity-aware search techniques, including best-first search, and generative models such as Generative Adversarial Networks (GANs). This book is primarily intended for scientists/researchers pursuing research in artificial intelligence and cognitive sciences. It is also useful for general readers/hobbyists in computer science and electronics engineering, for its useful and interesting contents on scientific creativity.
Sayantani Ghosh
Scientific creativity Brain connectivity Deep learning Graph convolution network Capsule network Type-2 fuzzy set Pattern classification Best first search Generative adversarial network