Skip to content
FREE SHIPPING ON ALL DOMESTIC ORDERS $35+
FREE SHIPPING ON ALL US ORDERS $35+
The Self-Assembling Brain: How Neural Networks Grow Smarter - Paperback | Diverse Reads

The Self-Assembling Brain: How Neural Networks Grow Smarter

Availability:
in stock, ready to be shipped
$24.95 - $24.95
$24.95
$28.99
$28.99 - $28.99
$28.99

ISBN-13: 9780691241692

Media Type: Paperback

Publisher: Princeton University Press

Publication Date: 12-13-2022

Pages: 384

Product Dimensions: 6.10(w) x 9.10(h) x 1.00(d)

Peter Robin Hiesinger is professor of neurobiology at Freie Universität Berlin, where he teaches undergraduate and graduate students and leads a research laboratory and a multilab research consortium on neural networks.

What People are Saying About This

From the Publisher

"The Self-Assembling Brain considers an interesting and timely topic—the relationship between what we know about how biological brains develop and the principles by which artificial intelligence networks are designed. Beginning with a fascinating historical debate, this book takes an ambitious look at a big and important area. I learned many things from new and diverse perspectives, which is exactly what I would expect from a book like this."—Kevin J. Mitchell, author of Innate

"Is the structure of the adult human brain a sufficient model for building artificially intelligent neural networks? Absolutely not is the message of The Self-Assembling Brain. Developmental processes are shown to be central to learning, both in the growth of the brain and continuing through in adult intelligence. This book could be a game changer."—Mark Lee, author of How to Grow a Robot



"This delightful book explores the underappreciated importance of algorithmic growth in understanding how biological systems develop and brains assemble. A significant contribution, The Self-Assembling Brain will interest readers in systems neuroscience, developmental neuroscience, and other areas of developmental biology, as well as computer scientists with an interest in biology."—Simon R. Schultz, Imperial College London

Table of Contents

Acknowledgments xi

Prologue xiii

Introduction 1

The Perspective of Neurobiological Information 4

The Perspective of Algorithmic Information 5

A Shared Perspective 7

The Ten Seminars 11

On Common Ground 24

The Present and the Past 26

The First Discussion: On Communication 26

The Historical Seminar: The Deeply Engrained Worship of Tidy-Looking Dichotomies 36

1 Algorithmic Growth 81

1.1 Information? What Information? 83

The Second Discussion: On Complexity 83

Seminar 2: From Algorithmic Growth to Endpoint Information 91

1.2 Noise and Relevant Information 112

The Third Discussion: On Apple Trees and the Immune System 112

Seminar 3: From Randomness to Precision 120

1.3 Autonomous Agents and Local Rules 139

The Fourth Discussion: On Filopodia and Soccer Games 139

Seminar 4: From Local Rules to Robustness 146

2 Of Players and Rules 161

2.1 The Benzer Paradox 163

The Fifth Discussion: On the Genetic Encoding of Behavior 163

Seminar 5: From Molecular Mechanisms to Evolutionary Programming 170

2.2 The Molecules That Could 186

The Sixth Discussion: On Guidance Cues and Target Recognition 186

Seminar 6: From Chemoaffinity to the Virtues of Permissiveness 192

2.3 The Levels Problem 211

The Seventh Discussion: On Context 211

Seminar 7: From Genes to Cells to Circuits 217

3 Brain Development and Artificial Intelligence 237

3.1 You Are Your History 239

The Eighth Discussion: On Development and the Long Reach of the Past 239

Seminar 8: From Development to Function 245

3.2 Self-Assembly versus "Build First, Train Later" 262

The Ninth Discussion: On the Growth of Artificial Neural Networks 262

Seminar 9: From Algorithmic Growth to Artificial Intelligence 267

3.3 Final Frontiers: Beloved Beliefs and the AI-Brain Interface 287

The Tenth Discussion: On Connecting the Brain and AI 287

Seminar 10: From Cognitive Bias to Whole Brain Emulation 294

Epilogue 312

Glossary 317

References 329

Index 351