Principles Of Artificial Neural Networks : Basic Designs To Deep LearningThe field of Artificial Neural Networks is the fastest growing field in Information Technology and specifically, in Artificial Intelligence and Machine Learning.This must-have compendium presents the theory and case studies of artificial neural networks. The volume, with 4 new chapters, updates the earlier edition by highlighting recent developments in Deep-Learning Neural Networks, which are the recent leading approaches to neural networks. Uniquely, the book also includes case studies of applications of neural networks — demonstrating how such case studies are designed, executed and how their results are obtained.The title is written for a one-semester graduate or senior-level undergraduate course on artificial neural networks. It is also intended to be a self-study and a reference text for scientists, engineers and for researchers in medicine, finance and data mining. |
Contents
| 1 | |
| 5 | |
| 9 | |
Chapter 4 The Perceptron | 17 |
Chapter 5 The Madaline | 37 |
Chapter 6 Back Propagation | 59 |
Chapter 7 Hopfield Networks | 123 |
Chapter 8 Counter Propagation | 185 |
Chapter 12 Recurrent Time Cycling Back Propagation Networks | 255 |
Principles and Scope | 271 |
Chapter 14 Deep Learning Convolutional Neural Network | 279 |
Chapter 15 LAMSTAR Neural Networks | 293 |
Chapter 16 Performance of DLNN Comparative Case Studies | 319 |
Problems | 395 |
| 401 | |
| 415 | |
Chapter 9 Adaptive Resonance Theory | 203 |
Chapter 10 The Cognitron and Neocognitron | 233 |
Chapter 11 Statistical Training | 239 |
Other editions - View all
Principles of Artificial Neural Networks: Basic Designs to Deep Learning Daniel Graupe No preview available - 2019 |
Common terms and phrases
activation function algorithm applications ART-I artificial neural networks Back Propagation BigDecimal binary biological neural network cell Chap characters classification CNN network Cognitron computational speed conf[i considered convergence Convolution Layer counter cout database dataset sn][j datatrue sn deep learning neural denoting DLNN employed end end end endl energy function error expectedOutputs feature map for(int given Graupe Hence hidden layer Hopfield network initial input layer input vector input word Kohonen layer labelMap LAMSTAR network LAMSTAR-1 learning neural networks link weights LNN-1 and LNN-2 local minima Lyapunov stability Madaline Matlab module N_LAYERS Neocognitron noise output decision output layer parameters pattern Perceptron performance predict preprocessing problem processing random recognition RECOGNIZED TRAINING VECTOR sigmoid function simulated annealing speech recognition stochastic structure Study sub-word testing training data training set update void w_hidden w_hidden_min w_output winning neuron z_output_min θε