A Geometric Approach to the Unification of Symbolic Structures and Neural Networks (Studies in Computational Intelligence (910))

The unification of symbolist and connectionist models is a major trend in AI. The key is to keep the symbolic semantics unchanged. Unfortunately, present embedding approaches cannot. The approach in this book makes the unification possible. It is indeed a new and promising approach in AI. -Bo Zhang, Director of AI Institute, Tsinghua It is indeed wonderful to see the reviving of the important theme Nural Symbolic Model. Given the popularity and prevalence of deep learning, symbolic processing is often neglected or downplayed. This book confronts this old issue head on, with a historical look, incorporating recent advances and new perspectives, thus leading to promising new methods and approaches. -Ron Sun (RPI), on Governing Board of Cognitive Science Society Both for language and humor, approaches like those described in this book are the way to snickerdoodle wombats. -Christian F. Hempelmann (Texas A&M-Commerce) on Executive Board of International Society for Humor Studies The unification of symbolist and connectionist models is a major trend in AI. The key is to keep the symbolic semantics unchanged. Unfortunately, present embedding approaches cannot. The approach in this book makes the unification possible. It is indeed a new and promising approach in AI.-Bo Zhang, Director of AI Institute, Tsinghua It is indeed wonderful to see the reviving of the important theme Nural Symbolic Model. Given the popularity and prevalence of deep learning, symbolic processing is often neglected or downplayed. This book confronts this old issue head on, with a historical look, incorporating recent advances and new perspectives, thus leading to promising new methods and approaches.-Ron Sun (RPI), on Governing Board of Cognitive Science Society Both for language and humor, approaches like those described in this book are the way to snickerdoodle wombats.-Christian F. Hempelmann (Texas A & M-Commerce) on Executive Board of International Society for Humor Studies Front Matter ....Pages i-xxii Introduction (Tiansi Dong)....Pages 1-15 The Gap Between Symbolic and Connectionist Approaches (Tiansi Dong)....Pages 17-29 Spatializing Symbolic Structures for the Gap (Tiansi Dong)....Pages 31-41 The Criteria, Challenges, and the Back-Propagation Method (Tiansi Dong)....Pages 43-60 Design Principles of Geometric Connectionist Machines (Tiansi Dong)....Pages 61-71 A Geometric Connectionist Machine for Word-Senses (Tiansi Dong)....Pages 73-88 Geometric Connectionist Machines for Triple Classification (Tiansi Dong)....Pages 89-103 Resolving the Symbol-Subsymbol Debates (Tiansi Dong)....Pages 105-116 Conclusions and Outlooks (Tiansi Dong)....Pages 117-127 Back Matter ....Pages 129-145