Normal view MARC view ISBD view

The self-assembling brain : how neural networks grow smarter / Peter Robin Hiesinger.

By: Hiesinger, Peter Robin [author.].
Material type: materialTypeLabelBookPublisher: Princeton : Princeton University Press, [2021]Copyright date: �2021Description: 1 online resource (xvi, 364 pages) : illustrations (black and white).Content type: text Media type: computer Carrier type: online resourceISBN: 0691215510; 9780691215518.Subject(s): Neural networks (Computer science) | Neural circuitry -- Adaptation | Learning -- Physiological aspects | Artificial intelligence | Neural Networks, Computer | Artificial Intelligence | R�eseaux neuronaux (Informatique) | R�eseaux nerveux -- Adaptation | Apprentissage -- Aspect physiologique | Intelligence artificielle | artificial intelligence | SCIENCE / Life Sciences / Neuroscience | Learning -- Physiological aspects | Artificial intelligence | Neural circuitry -- Adaptation | Neural networks (Computer science)Genre/Form: Electronic books. | Electronic books.Additional physical formats: Print version:: The self-assembling brainDDC classification: 006.3/2 Online resources: Click here to access online
Contents:
Frontmatter -- Contents -- Acknowledgments -- Prologue -- The self-assembling brain -- Introduction -- The Present and the Past -- 1 Algorithmic growth -- 2 Of players and rules -- 3 Brain development and artificial intelligence -- Epilogue -- Glossary -- References -- Index
Summary: "In this book, Peter Robin Hiesinger explores historical and contemporary attempts to understand the information needed to make biological and artificial neural networks. Developmental neurobiologists and computer scientists with an interest in artificial intelligence - driven by the promise and resources of biomedical research on the one hand, and by the promise and advances of computer technology on the other - are trying to understand the fundamental principles that guide the generation of an intelligent system. Yet, though researchers in these disciplines share a common interest, their perspectives and approaches are often quite different. The book makes the case that "the information problem" underlies both fields, driving the questions that are driving forward the frontiers, and aims to encourage cross-disciplinary communication and understanding, to help both fields make progress. The questions that challenge researchers in these fields include the following. How does genetic information unfold during the years-long process of human brain development, and can this be a short-cut to create human-level artificial intelligence? Is the biological brain just messy hardware that can be improved upon by running learning algorithms in computers? Can artificial intelligence bypass evolutionary programming of "grown" networks? These questions are tightly linked, and answering them requires an understanding of how information unfolds algorithmically to generate functional neural networks. Via a series of closely linked "discussions" (fictional dialogues between researchers in different disciplines) and pedagogical "seminars," the author explores the different challenges facing researchers working on neural networks, their different perspectives and approaches, as well as the common ground and understanding to be found amongst those sharing an interest in the development of biological brains and artificial intelligent systems"-- Provided by publisher.
    average rating: 0.0 (0 votes)
No physical items for this record

Includes bibliographical references and index.

"In this book, Peter Robin Hiesinger explores historical and contemporary attempts to understand the information needed to make biological and artificial neural networks. Developmental neurobiologists and computer scientists with an interest in artificial intelligence - driven by the promise and resources of biomedical research on the one hand, and by the promise and advances of computer technology on the other - are trying to understand the fundamental principles that guide the generation of an intelligent system. Yet, though researchers in these disciplines share a common interest, their perspectives and approaches are often quite different. The book makes the case that "the information problem" underlies both fields, driving the questions that are driving forward the frontiers, and aims to encourage cross-disciplinary communication and understanding, to help both fields make progress. The questions that challenge researchers in these fields include the following. How does genetic information unfold during the years-long process of human brain development, and can this be a short-cut to create human-level artificial intelligence? Is the biological brain just messy hardware that can be improved upon by running learning algorithms in computers? Can artificial intelligence bypass evolutionary programming of "grown" networks? These questions are tightly linked, and answering them requires an understanding of how information unfolds algorithmically to generate functional neural networks. Via a series of closely linked "discussions" (fictional dialogues between researchers in different disciplines) and pedagogical "seminars," the author explores the different challenges facing researchers working on neural networks, their different perspectives and approaches, as well as the common ground and understanding to be found amongst those sharing an interest in the development of biological brains and artificial intelligent systems"-- Provided by publisher.

Description based on online resource; title from digital title page (viewed on May 11, 2021).

Frontmatter -- Contents -- Acknowledgments -- Prologue -- The self-assembling brain -- Introduction -- The Present and the Past -- 1 Algorithmic growth -- 2 Of players and rules -- 3 Brain development and artificial intelligence -- Epilogue -- Glossary -- References -- Index

IEEE IEEE Xplore Princeton University Press eBooks Library

There are no comments for this item.

Log in to your account to post a comment.