Ebook: Neural Computers

the outcome of a NATO Advanced Research Workshop (ARW) This book is held in Neuss (near Dusseldorf), Federal Republic of Germany from 28 September to 2 October, 1987. The workshop assembled some 50 invited experts from Europe, Ameri­ ca, and Japan representing the fields of Neuroscience, Computational Neuroscience, Cellular Automata, Artificial Intelligence, and Compu­ ter Design; more than 20 additional scientists from various countries attended as observers. The 50 contributions in this book cover a wide range of topics, including: Neural Network Architecture, Learning and Memory, Fault Tolerance, Pattern Recognition, and Motor Control in Brains versus Neural Computers. Twelve of these contributions are review papers. The readability of this book was enhanced by a number of measures: * The contributions are arranged in seven chapters. * A separate List of General References helps newcomers to this ra­ pidly growing field to find introductory books. * The Collection of References from all Contributions provides an alphabetical list of all references quoted in the individual con­ tributions. * Separate Reference Author and Subject Indices facilitate access to various details. Group Reports (following the seven chapters) summarize the discus­ sions regarding four specific topics relevant for the 'state of the art' in Neural Computers.

---

The soft cover study edition now available is a revised reprint of the successful first edition of 1988. It collects invited presentations of an Advanced Research Workshop on "Neural Computers", held in Neuss, Federal Republic of Germany, September 28 - October 2, 1987. The objectives of the workshop were - to promote international collaboration among scientists from the fields of Neuroscience, Computational Neuroscience, Cellular Automata, Artificial Intelligence, and Computer Design; and - to review our present knowledge of brain research and novel computers with neural network architecture. The workshop assembled some fifty invited experts from Europe, America and Japan representing the relevant fields. The book describes the transfer of concepts of brain function and brain architecture to the design of self-organizing computers with neural network architecture. The contributions cover a wide range of topics, including Neural Network Architecture, Learning and Memory, Fault Tolerance, Pattern Recognition, and Motor Control in Brains Versus Neural Computers. Twelve of the contributions are review papers. In addition, group reports summarize the discussions regarding four specific topics relevant to the state of the art in neural computers. With its extensive reference list as well as its subject and name indexes this volume will serve as a reference book for future research in the field of Neural Computers.

---

The soft cover study edition now available is a revised reprint of the successful first edition of 1988. It collects invited presentations of an Advanced Research Workshop on "Neural Computers", held in Neuss, Federal Republic of Germany, September 28 - October 2, 1987. The objectives of the workshop were - to promote international collaboration among scientists from the fields of Neuroscience, Computational Neuroscience, Cellular Automata, Artificial Intelligence, and Computer Design; and - to review our present knowledge of brain research and novel computers with neural network architecture. The workshop assembled some fifty invited experts from Europe, America and Japan representing the relevant fields. The book describes the transfer of concepts of brain function and brain architecture to the design of self-organizing computers with neural network architecture. The contributions cover a wide range of topics, including Neural Network Architecture, Learning and Memory, Fault Tolerance, Pattern Recognition, and Motor Control in Brains Versus Neural Computers. Twelve of the contributions are review papers. In addition, group reports summarize the discussions regarding four specific topics relevant to the state of the art in neural computers. With its extensive reference list as well as its subject and name indexes this volume will serve as a reference book for future research in the field of Neural Computers.
Content:
Front Matter....Pages I-XIII
The Role of Adaptive and Associative Circuits in Future Computer Designs....Pages 1-8
Faust, Mephistopheles and Computer....Pages 9-16
Structured Neural Networks in Nature and in Computer Science....Pages 17-21
Goal and Architecture of Neural Computers....Pages 23-28
Conventional Fault-Tolerance and Neural Computers....Pages 29-37
Fault-Tolerance in Imaging-Oriented Systolic Arrays....Pages 39-50
Parallelism and Redundancy in Neural Networks....Pages 51-60
Relational Models in Natural and Artificial Vision....Pages 61-70
Image Segmentation with Neurocomputers....Pages 71-79
A Hierarchical Neural Network Model for Selective Attention....Pages 81-90
Mapping Images to a Hierarchical Data Structure — A Way to Knowledge-Based Pattern Recognition....Pages 91-100
Computing Motion in the Presence of Discontinuities: Algorithm and Analog Networks....Pages 101-110
Design Principles for a Front-End Visual System....Pages 111-118
Towards a Primal Sketch of Real World Scenes in Early Vision....Pages 119-128
Why Cortices ? Neural Computation in the Vertebrate Visual System....Pages 129-138
A Cortical Network Model for Early Vision Processing....Pages 139-148
Image Segregation by Motion : Cortical Mechanisms and Implementation in Neural Networks....Pages 149-158
On the Acquisition of Object Concepts from Sensory Data....Pages 159-168
Neural Computers in Vision: Processing of High Dimensional Data....Pages 169-178
Computational Networks in Early Vision: From orientation selection to optical flow....Pages 179-188
Logical Connectionist Systems....Pages 189-197
Backpropagation in Perceptrons with Feedback....Pages 199-208
A Neural Model with Multiple Memory Domains....Pages 209-217
The Never-Ending Learning....Pages 219-230
Storing Sequences of Biased Patterns in Neural Networks with Stochastic Dynamics....Pages 231-242
The Inverse Problem for Linear Boolean Nets....Pages 243-250
Training with Noise: Application to Word and Text Storage....Pages 251-260
Of Points and Loops....Pages 261-269
On the Asymptotic Information Storage Capacity of Neural Networks....Pages 271-280
Learning Networks of Neurons with Boolean Logic....Pages 281-289
Neural Network Learning Algorithms....Pages 291-300
Exploring Three Possibilities in Network Design: Spontaneous Node Activity, Node Plasticity and Temporal Coding....Pages 301-310
Schemas and Neurons: Two Levels of Neural Computing....Pages 311-320
Applications of Concurrent Neuromorphic Algorithms for Autonomous Robots....Pages 321-333
The Relevance of Mechanical Sensors for Neural Generation of Movements in Space....Pages 335-344
Spatial and Temporal Transformations in Visuo-Motor Coordination....Pages 345-357
Neural Networks for Motor Program Generation....Pages 359-370
Innate and Learned Components in a Simple Visuo-Motor Reflex....Pages 371-380
Tensor Geometry: A Language of Brains & Neurocomputers. Generalized Coordinates in Neuroscience & Robotics....Pages 381-391
Extending Kohonen’s Self-Organizing Mapping Algorithm to Learn Ballistic Movements....Pages 393-406
Limited Interconnectivity in Synthetic Neural Systems....Pages 407-416
Nonlinear Optical Neural Networks: Dynamic Ring Oscillators....Pages 417-424
Dynamical Properties of a New Type of Neural Network....Pages 425-433
A Dedicated Computer for Simulation of Large Systems of Neural Nets....Pages 435-444
Neurocomputer Applications....Pages 445-453
Asynchrony and Concurrency....Pages 455-465
Implementations of Neural Network Models in Silicon....Pages 467-476
The Transputer....Pages 477-486
Parallel Architectures for Neural Computers....Pages 487-495
Control of the immune response....Pages 497-501
Group Report 1: Structure in Neural Networks....Pages 503-504
Group Report 2: General Software for the Simulation of Neural Nets....Pages 505-506
Group Report 3: Hardware (e.g. Transputer Based) for Neural Computing....Pages 507-508
Group Report 4: Typical Applications of Neural Computers....Pages 509-509
Back Matter....Pages 511-566

---

The soft cover study edition now available is a revised reprint of the successful first edition of 1988. It collects invited presentations of an Advanced Research Workshop on "Neural Computers", held in Neuss, Federal Republic of Germany, September 28 - October 2, 1987. The objectives of the workshop were - to promote international collaboration among scientists from the fields of Neuroscience, Computational Neuroscience, Cellular Automata, Artificial Intelligence, and Computer Design; and - to review our present knowledge of brain research and novel computers with neural network architecture. The workshop assembled some fifty invited experts from Europe, America and Japan representing the relevant fields. The book describes the transfer of concepts of brain function and brain architecture to the design of self-organizing computers with neural network architecture. The contributions cover a wide range of topics, including Neural Network Architecture, Learning and Memory, Fault Tolerance, Pattern Recognition, and Motor Control in Brains Versus Neural Computers. Twelve of the contributions are review papers. In addition, group reports summarize the discussions regarding four specific topics relevant to the state of the art in neural computers. With its extensive reference list as well as its subject and name indexes this volume will serve as a reference book for future research in the field of Neural Computers.
Content:
Front Matter....Pages I-XIII
The Role of Adaptive and Associative Circuits in Future Computer Designs....Pages 1-8
Faust, Mephistopheles and Computer....Pages 9-16
Structured Neural Networks in Nature and in Computer Science....Pages 17-21
Goal and Architecture of Neural Computers....Pages 23-28
Conventional Fault-Tolerance and Neural Computers....Pages 29-37
Fault-Tolerance in Imaging-Oriented Systolic Arrays....Pages 39-50
Parallelism and Redundancy in Neural Networks....Pages 51-60
Relational Models in Natural and Artificial Vision....Pages 61-70
Image Segmentation with Neurocomputers....Pages 71-79
A Hierarchical Neural Network Model for Selective Attention....Pages 81-90
Mapping Images to a Hierarchical Data Structure — A Way to Knowledge-Based Pattern Recognition....Pages 91-100
Computing Motion in the Presence of Discontinuities: Algorithm and Analog Networks....Pages 101-110
Design Principles for a Front-End Visual System....Pages 111-118
Towards a Primal Sketch of Real World Scenes in Early Vision....Pages 119-128
Why Cortices ? Neural Computation in the Vertebrate Visual System....Pages 129-138
A Cortical Network Model for Early Vision Processing....Pages 139-148
Image Segregation by Motion : Cortical Mechanisms and Implementation in Neural Networks....Pages 149-158
On the Acquisition of Object Concepts from Sensory Data....Pages 159-168
Neural Computers in Vision: Processing of High Dimensional Data....Pages 169-178
Computational Networks in Early Vision: From orientation selection to optical flow....Pages 179-188
Logical Connectionist Systems....Pages 189-197
Backpropagation in Perceptrons with Feedback....Pages 199-208
A Neural Model with Multiple Memory Domains....Pages 209-217
The Never-Ending Learning....Pages 219-230
Storing Sequences of Biased Patterns in Neural Networks with Stochastic Dynamics....Pages 231-242
The Inverse Problem for Linear Boolean Nets....Pages 243-250
Training with Noise: Application to Word and Text Storage....Pages 251-260
Of Points and Loops....Pages 261-269
On the Asymptotic Information Storage Capacity of Neural Networks....Pages 271-280
Learning Networks of Neurons with Boolean Logic....Pages 281-289
Neural Network Learning Algorithms....Pages 291-300
Exploring Three Possibilities in Network Design: Spontaneous Node Activity, Node Plasticity and Temporal Coding....Pages 301-310
Schemas and Neurons: Two Levels of Neural Computing....Pages 311-320
Applications of Concurrent Neuromorphic Algorithms for Autonomous Robots....Pages 321-333
The Relevance of Mechanical Sensors for Neural Generation of Movements in Space....Pages 335-344
Spatial and Temporal Transformations in Visuo-Motor Coordination....Pages 345-357
Neural Networks for Motor Program Generation....Pages 359-370
Innate and Learned Components in a Simple Visuo-Motor Reflex....Pages 371-380
Tensor Geometry: A Language of Brains & Neurocomputers. Generalized Coordinates in Neuroscience & Robotics....Pages 381-391
Extending Kohonen’s Self-Organizing Mapping Algorithm to Learn Ballistic Movements....Pages 393-406
Limited Interconnectivity in Synthetic Neural Systems....Pages 407-416
Nonlinear Optical Neural Networks: Dynamic Ring Oscillators....Pages 417-424
Dynamical Properties of a New Type of Neural Network....Pages 425-433
A Dedicated Computer for Simulation of Large Systems of Neural Nets....Pages 435-444
Neurocomputer Applications....Pages 445-453
Asynchrony and Concurrency....Pages 455-465
Implementations of Neural Network Models in Silicon....Pages 467-476
The Transputer....Pages 477-486
Parallel Architectures for Neural Computers....Pages 487-495
Control of the immune response....Pages 497-501
Group Report 1: Structure in Neural Networks....Pages 503-504
Group Report 2: General Software for the Simulation of Neural Nets....Pages 505-506
Group Report 3: Hardware (e.g. Transputer Based) for Neural Computing....Pages 507-508
Group Report 4: Typical Applications of Neural Computers....Pages 509-509
Back Matter....Pages 511-566
....