Neural networks - Info and Reading Options

"Neural networks" Table Of Contents:

• 1- Models of Neural Networks
• 2- The Structure of the Central Nervous System
• 3- The Neuron
• 4- The Cerebral Cortex
• 5- Neural Networks Introduced
• 6- A Definition
• 7- A Brief History of Neural Network Models
• 8- Why Neural Networks?
• 9- Parallel Distributed Processing
• 10- Understanding How the Brain Works
• 11- General Literature on Neural Network Models
• 12- Associative Memory
• 13- Associative Information Storage and Recall
• 14- Learning by Hebb's Rule
• 15- Neurons and Spins
• 16- The "Magnetic" Connection
• 17- Parallel versus Sequential Dynamics
• 18- Neural "Motion Pictures"
• 19- Stochastic Neurons
• 20- The Mean-Field Approximation
• 21- Single Patterns
• 22- Several Patterns
• 23- Cybernetic Networks
• 24- Layered Networks
• 25- Simple Perceptrons
• 26- The Perceptron Learning Rule
• 27- "Gradient" Learning
• 28- A Counterexample: The Exclusive-OR Gate
• 29- Multilayered Perceptrons
• 30- Solution of the XOR Problem
• 31- Learning by Error Back-Propagation
• 32- Boolean Functions
• 33- Representation of Continuous Functions
• 34- Applications
• 35- Prediction of Time Series
• 36- The Logistic Map
• 37- A Nonlinear Delayed Differential Equation
• 38- Nonlinear Prediction of Noisy Time Series
• 39- Learning to Play Backgammon
• 40- Prediction of the Secondary Structure of Proteins
• 41- Net-Talk: Learning to Pronounce English Text
• 42- More Applications of Neural Networks
• 43- Neural Networks in High Energy Physics
• 44- The Search for Heavy Quarks
• 45- Triggering
• 46- Mass Reconstruction
• 47- The Jetnet Code
• 48- Pattern Recognition
• 49- Handwriting and Text Recognition
• 50- Speech Recognition
• 51- 3D Target Classification and Reconstruction
• 52- Neural Networks in Biomedicine
• 53- Neural Networks in Economics
• 54- Network Architecture and Generalization
• 55- Building the Network
• 56- Dynamic Node Creation
• 57- Learning by Adding Neurons
• 58- Can Neural Networks Generalize?
• 59- General Aspects
• 60- Generalization and Information Theory
• 61- Invariant Pattern Recognition
• 62- Higher-Order Synapses
• 63- Preprocessing the Input Patterns
• 64- Associative Memory: Advanced Learning Strategies
• 65- Storing Correlated Patterns
• 66- The Projection Rule
• 67- An Iterative Learning Scheme
• 68- Repeated Hebbian Learning
• 69- Special Learning Rules
• 70- Forgetting Improves the Memory!
• 71- Nonlinear Learning Rules
• 72- Dilution of Synapses
• 73- Networks with a Low Level of Activity
• 74- Combinatorial Optimization
• 75- NP-Complete Problems
• 76- Optimization by Simulated Annealing
• 77- Realization on a Network
• 78- The Traveling-Salesman Problem
• 79- Optical Image Processing
• 80- VLSI and Neural Networks
• 81- Hardware for Neural Networks
• 82- Networks Composed of Analog Electronic Circuits
• 83- Symmetrical Networks with Hidden Neurons
• 84- The Boltzmann Machine
• 85- The "Boltzmann" Learning Rule
• 86- Applications
• 87- Coupled Neural Networks
• 88- Stationary States
• 89- Recurrent Back-Propagation
• 90- Back-Propagation Through Time
• 91- Network Hierarchies
• 92- Unsupervised Learning
• 93- "Selfish" Neurons
• 94- Learning by Competition
• 95- "The Winner Takes All"
• 96- Structure Formation by Local Inhibition
• 97- The Kohonen Map
• 98- Implementations of Competitive Learning
• 99- A Feature-Sensitive Mapping Network
• 100- The Neocognitron
• 101- Evolutionary Algorithms for Learning
• 102- Why Do Evolutionary Algorithms Work?
• 103- Evolving Neural Networks
• 104- Feed-Forward Networks
• 105- Recurrent Networks
• 106- Evolving Back-Propagation
• 107- Statistical Physics of Neural Networks
• 108- Statistical Physics and Spin Glasses
• 109- Elements of Statistical Mechanics
• 110- Spin Glasses
• 111- Averages and Ergodicity
• 112- The Edwards-Anderson Model
• 113- The Hopfield Network for p/N -> 0
• 114- Evaluation of the Partition Function
• 115- Equilibrium States of the Network
• 116- The Hopfield Network for Finite p/N
• 117- The Replica Trick
• 118- Averaging over Patterns
• 119- The Saddle-Point Approximation
• 120- Phase Diagram of the Hopfield Network
• 121- Storage Capacity of Nonlinear Neural Networks
• 122- The Dynamics of Pattern Retrieval
• 123- Asymmetric Networks
• 124- Highly Diluted Networks
• 125- The Fully Coupled Network
• 126- The Space of Interactions in Neural Networks
• 127- Replica Solution of the Spherical Model
• 128- Results
• 129- Computer Codes
• 130- Numerical Demonstrations
• 131- How to Use the Computer Programs
• 132- Notes on the Software Implementation
• 133- Asso: Associative Memory
• 134- Program Description
• 135- Numerical Experiments
• 136- Asscount: Associative Memory for Time Sequences
• 137- Program Description
• 138- Numerical Experiments
• 139- Perbool: Learning Boolean Functions with Back-Prop
• 140- Program Description
• 141- Numerical Experiments
• 142- Perfunc: Learning Continuous Functions with Back-Prop
• 143- Program Description
• 144- Numerical Experiments
• 145- Solution of the Traveling-Salesman Problem
• 146- The Hopfield-Tank Model
• 147- TSPHop: Program Description
• 148- The Potts-Glass Model
• 149- The Mean-Field Approximation of the Potts Model
• 150- TSPOtts: Program Description
• 151- TSAnneal: Simulated Annealing
• 152- Numerical Experiments
• 153- Kohomap: The Kohonen Self-Organizing Map
• 154- Program Description
• 155- Numerical Experiments
• 156- BTT: Back-Propagation Through Time
• 157- Program Description
• 158- Numerical Experiments
• 159- Neurogen: Using Genetic Algorithms to Train Networks
• 160- Program Description
• 161- References
• 162- Index

Read “Neural networks”:

Read “Neural networks” by choosing from the options below.