دانلود کتاب Neuromorphic Engineering: The Scientist’s, Algorithms Designer’s and Computer Architect’s Perspectives on Brain-Inspired Computing

فهرست مطالب :

Cover\nHalf Title\nTitle Page\nCopyright Page\nDedication\nContents\nAbout the author\nPreface\nForeword: a tale about passion and fear\nList of Figures\nBefore we begin\nGlossary\nSection I: Introduction and Overview\n Chapter 1: Introducing the perspective of the scientist\n 1.1. FROM THE NEURON DOCTRINE TO EMERGENT BEHAVIOR\n 1.1.1. The unity and diversity of neurons\n 1.1.2. Neural coding\n 1.1.3. Networks and emergent behavior\n 1.1.4. Neuronal abstractions\n 1.1.5. Data-driven neuroscience\n 1.2. BRAIN MODELING\n 1.2.1. Brain modeling in biological systems\n 1.2.2. Computational brain modeling\n 1.2.2.1. Bottom-up modeling\n 1.2.2.2. Top-down modeling\n 1.2.3. Brain modeling with neuromorphic hardware\n 1.3. GLOSSARY\n 1.4. FURTHER READING\n Chapter 2: Introducing the perspective of the computer architect\n 2.1. LIMITS OF INTEGRATED CIRCUITS\n 2.1.1. Transistor density\n 2.1.2. Processing speed\n 2.1.3. Distributed computing\n 2.2. EMERGING COMPUTING PARADIGMS\n 2.2.1. Quantum computing\n 2.2.2. Molecular computing\n 2.2.3. DNA computing\n 2.2.4. Programmable microfluidics\n 2.3. BRAIN-INSPIRED HARDWARE\n 2.3.1. The why\n 2.3.2. The how\n 2.3.2.1. Probabilistic representation\n 2.3.2.2. In-memory computing\n 2.3.3. The what\n 2.3.4. Neuromorphic frameworks\n 2.3.4.1. Neuromorphic sensing\n 2.3.4.2. Neuromorphic interfaces\n 2.3.4.3. General purpose neuromorphic computers\n 2.3.4.4. Memristors\n 2.4. GLOSSARY\n 2.5. FURTHER READING\n Chapter 3: Introducing the perspective of the algorithm designer\n 3.1. FROM ARTIFICIAL TO SPIKING NEURAL NETWORKS\n 3.1.1. Network architecture\n 3.1.2. Neuromorphic applications\n 3.1.2.1. Neuromorphic learning\n 3.1.2.2. Neuro-robotics\n 3.1.2.3. Cognitive models\n 3.2. NEUROMORPHIC SOFTWARE DEVELOPMENT\n 3.3. GLOSSARY\n 3.4. FURTHER READING\nSection II: The Scientist’s Perspective\n Chapter 4: Biological description of neuronal dynamics\n 4.1. POTENTIALS AND SPIKES\n 4.1.1. The resting potential\n 4.1.2. The action potential\n 4.1.3. Spike propagation\n 4.1.4. Synapses\n 4.2. POWER AND PERFORMANCE ESTIMATES OF THE BRAIN\n 4.3. GLOSSARY\n 4.4. FURTHER READING\n Chapter 5: Models of point neuronal dynamic\n 5.1. THE LEAKY INTEGRATE AND FIRE MODEL\n 5.1.1. Membrane voltage for various input patterns\n 5.1.2. Flat input\n 5.1.3. Step current input\n 5.1.4. Numerical modeling of pulse input\n 5.1.5. Arbitrary input\n 5.2. THE IZHIKEVICH NEURON MODEL\n 5.3. THE HODGKIN-HUXLEY MODEL\n 5.4. SYNAPSE MODELING\n 5.5. SIMULATING POINT NEURONS\n 5.5.1. Biological plausibility vs. computational resources\n 5.5.2. Large scale simulations of point processes\n 5.6. CASE STUDY: A SNN FOR PERCEPTUAL FILLING-IN\n 5.6.1. Perceptual filling-in\n 5.6.2. Mathematical formulation\n 5.6.3. Feed-forward SNN for perceptual filling-in\n 5.6.4. Recurrent SNN for perceptual filling-in\n 5.6.5. Is it biologically plausible?\n 5.7. GLOSSARY\n 5.8. FURTHER READING\n Chapter 6: Models of morphologically detailed neurons\n 6.1. WHY MORPHOLOGICALLY DETAILED MODELING?\n 6.2. THE CABLE EQUATION\n 6.2.1. Passive Dendrite\n 6.2.2. Axon\n 6.2.3. Simulating the cable equation\n 6.2.4. Partition length\n 6.3. THE COMPARTMENTAL MODEL\n 6.3.1. Reconstructed morphology and dynamic\n 6.4. CASE STUDY: DIRECTIONAL SELECTIVE SAC\n 6.5. GLOSSARY\n 6.6. FURTHER READING\n Chapter 7: Models of network dynamic and learning\n 7.1. NEURAL CIRCUIT TAXONOMY FOR BEHAVIOR\n 7.2. RECONSTRUCTION AND SIMULATION OF NEURAL NETWORKS\n 7.2.1. Detailed modeling\n 7.2.2. Simulating detailed models\n 7.3. CASE STUDY: SACS’ LATERAL INHIBITION IN DIRECTION SELECTIVITY\n 7.4. NEUROMORPHIC AND BIOLOGICAL LEARNING\n 7.4.1. Biological backpropagation-inspired learning\n 7.4.2. Biological unsupervised learning\n 7.4.2.1. Hebbian learning\n 7.4.2.2. Spike timing-dependent plasticity\n 7.4.2.3. BCM learning\n 7.4.2.4. Oja’s learning\n 7.5. GLOSSARY\n 7.6. FURTHER READING\nSection III: The Computer Architect’s Perspective\n Chapter 8: Neuromorphic hardware\n 8.1. TRANSISTORS AND MICRO-POWER CIRCUITRY\n 8.2. THE SILICON NEURON\n 8.2.1. The pulse current-source synapse\n 8.2.2. The reset and discharge synapse\n 8.2.3. The charge and discharge synapse\n 8.2.4. The log-domain integrator synapse\n 8.2.5. The axon-hillock neuron\n 8.2.6. Voltage-amplifier LIF neuron\n 8.3. CASE STUDY: HARDWARE AND SOFTWARE CO-SYNTHESIS\n 8.3.1. Circuit design\n 8.3.2. Circuit analysis\n 8.3.2.1. Architectural design\n 8.3.2.2. Neuron control\n 8.3.3. NEF-inspired design\n 8.4. GLOSSARY\n 8.5. FURTHER READING\n Chapter 9: Communication and hybrid circuit design\n 9.1. COMMUNICATING SILICON NEURONS\n 9.2. FROM HYBRID TO DIGITAL CIRCUITRY\n 9.3. GLOSSARY\n 9.4. FURTHER READING\n Chapter 10: In-memory computing with memristors\n 10.1. FROM TRANSISTORS TO MEMRISTORS\n 10.2. A NEW FUNDAMENTAL CIRCUIT ELEMENT\n 10.3. MEMRISTORS FOR NEUROMORPHIC ENGINEERING\n 10.4. GLOSSARY\n 10.5. FURTHER READING\nSection IV: The Algorithms Designer’s Perspective\n Chapter 11: Introduction to neuromorphic programming\n 11.1. THEORY OF NEUROMORPHIC COMPUTING\n 11.1.1. Neuromorphic computing as Turing complete\n 11.1.2. A complexity theory for neuromorphic computing\n 11.2. UNDERSTANDING NEUROMORPHIC PROGRAMMING\n 11.3. GLOSSARY\n 11.4. FURTHER READING\n Chapter 12: The Neural Engineering Framework (NEF)\n 12.1. THE FUNDAMENTAL PRINCIPLES OF NEF\n 12.1.1. Representation\n 12.1.1.1. Encoding\n 12.1.1.2. Decoding\n 12.1.1.3. Decoder analysis\n 12.1.1.4. Representation of high dimensional stimulus\n 12.1.2. Transformation\n 12.1.2.1. Linear transformation\n 12.1.2.2. Linear transformations\n 12.1.2.3. Non-linear transformations\n 12.1.2.4. Addition\n 12.1.2.5. Multiplication\n 12.1.3. Dynamics\n 12.1.3.1. The recurrent connection\n 12.1.3.2. Synthesis\n 12.1.3.3. Neuromorphic integration\n 12.1.3.4. Neuromorphic oscillators\n 12.1.3.5. Neuromorphic attractors\n 12.2. CASE STUDY: MOTION DETECTION IN A SPIKING CAMERA USING OSCILLATION INTERFERENCE\n 12.2.1. Spiking camera\n 12.2.2. Gabor functions\n 12.2.3. Damped oscillators\n 12.2.4. Motion detection\n 12.3. GLOSSARY\n 12.4. FURTHER READING\n Chapter 13: Learning spiking neural networks\n 13.1. INTRODUCTION TO LEARNING SNNS\n 13.2. LEARNING SPIKING NEURAL NETWORKS WITH NEF\n 13.2.1. The prescribed error sensitivity rule\n 13.2.2. PES learning for classical conditioning\n 13.3. FROM DNN TO DEEP SNN\n 13.3.1. MNIST classification with deep SNN\n 13.3.1.1. Convolutional neural networks\n 13.3.1.2. CNN architecture\n 13.3.1.3. Results\n 13.4. GLOSSARY\n 13.5. FURTHER READING\nBibliography\nIndex