SpringerLink

Incluye referencias bibliográficas

Preface; Contents; Acronyms; 1 Introduction; 1.1 Background; 1.2 Spiking Neurons; 1.2.1 Biological Background; 1.2.2 Generations of Neuron Models; 1.2.3 Spiking Neuron Models; 1.3 Neural Codes; 1.3.1 Rate Code; 1.3.2 Temporal Code; 1.3.3 Temporal Code Versus Rate Code; 1.4 Cognitive Learning and Memory in the Brain; 1.4.1 Temporal Learning; 1.4.2 Cognitive Memory in the Brain; 1.5 Objectives and Contributions; 1.6 Outline of the Book; References; 2 Rapid Feedforward Computation by Temporal Encoding and Learning with Spiking Neurons; 2.1 Introduction; 2.2 The Spiking Neural Network

2.3 Single-Spike Temporal Coding2.4 Temporal Learning Rule; 2.4.1 The Tempotron Rule; 2.4.2 The ReSuMe Rule; 2.4.3 The Tempotron-Like ReSuMe Rule; 2.5 Simulation Results; 2.5.1 The Data Set and the Classification Problem; 2.5.2 Encoding Images; 2.5.3 Choosing Among Temporal Learning Rules; 2.5.4 The Properties of Tempotron Rule; 2.5.5 Recognition Performance; 2.6 Discussion; 2.6.1 Encoding Benefits from Biology; 2.6.2 Types of Synapses; 2.6.3 Schemes of Readout; 2.6.4 Extension of the Network for Robust Sound Recognition; 2.7 Conclusion; References

3 A Spike-Timing Based Integrated Model for Pattern Recognition3.1 Introduction; 3.2 The Integrated Model; 3.2.1 Neuron Model and General Structure; 3.2.2 Latency-Phase Encoding; 3.2.3 Supervised Spike-Timing Based Learning; 3.3 Numerical Simulations; 3.3.1 Network Architecture and Encoding of Grayscale Images; 3.3.2 Learning Performance; 3.3.3 Generalization Capability; 3.3.4 Parameters Evaluation; 3.3.5 Capacity of the Integrated System; 3.4 Related Works; 3.5 Conclusions; References; 4 Precise-Spike-Driven Synaptic Plasticity for Hetero Association of Spatiotemporal Spike Patterns

4.1 Introduction4.2 Methods; 4.2.1 Spiking Neuron Model; 4.2.2 PSD Learning Rule; 4.3 Results; 4.3.1 Association of Single-Spike and Multi-spike Patterns; 4.3.2 Generality to Different Neuron Models; 4.3.3 Robustness to Noise; 4.3.4 Learning Capacity; 4.3.5 Effects of Learning Parameters; 4.3.6 Classification of Spatiotemporal Patterns; 4.4 Discussion and Conclusion; References; 5 A Spiking Neural Network System for Robust Sequence Recognition; 5.1 Introduction; 5.2 The Integrated Network for Sequence Recognition; 5.2.1 Rationale of the Whole System; 5.2.2 Neural Encoding Method

5.2.3 Item Recognition with the PSD Rule5.2.4 The Spike Sequence Decoding Method; 5.3 Experimental Results; 5.3.1 Learning Performance Analysis of the PSD Rule; 5.3.2 Item Recognition; 5.3.3 Spike Sequence Decoding; 5.3.4 Sequence Recognition System; 5.4 Discussions; 5.4.1 Temporal Learning Rules and Spiking Neurons; 5.4.2 Spike Sequence Decoding Network; 5.4.3 Potential Applications in Authentication; 5.5 Conclusion; References; 6 Temporal Learning in Multilayer Spiking Neural Networks Through Construction of Causal Connections; 6.1 Introduction; 6.2 Multilayer Learning Rules

This book presents neuromorphic cognitive systems from a learning and memory-centered perspective. It illustrates how to build a system network of neurons to perform spike-based information processing, computing, and high-level cognitive tasks. It is beneficial to a wide spectrum of readers, including undergraduate and postgraduate students and researchers who are interested in neuromorphic computing and neuromorphic engineering, as well as engineers and professionals in industry who are involved in the design and applications of neuromorphic cognitive systems, neuromorphic sensors and processors, and cognitive robotics. The book formulates a systematic framework, from the basic mathematical and computational methods in spike-based neural encoding, learning in both single and multi-layered networks, to a near cognitive level composed of memory and cognition. Since the mechanisms for integrating spiking neurons integrate to formulate cognitive functions as in the brain are little understood, studies of neuromorphic cognitive systems are urgently needed. The topics covered in this book range from the neuronal level to the system level. In the neuronal level, synaptic adaptation plays an important role in learning patterns. In order to perform higher-level cognitive functions such as recognition and memory, spiking neurons with learning abilities are consistently integrated, building a system with encoding, learning and memory functionalities. The book describes these aspects in detail.