Constructive Neural NetworksLeonardo Franco, José M. Jerez This book presents a collection of invited works that consider constructive methods for neural networks, taken primarily from papers presented at a special th session held during the 18 International Conference on Artificial Neural Networks (ICANN 2008) in September 2008 in Prague, Czech Republic. The book is devoted to constructive neural networks and other incremental learning algorithms that constitute an alternative to the standard method of finding a correct neural architecture by trial-and-error. These algorithms provide an incremental way of building neural networks with reduced topologies for classification problems. Furthermore, these techniques produce not only the multilayer topologies but the value of the connecting synaptic weights that are determined automatically by the constructing algorithm, avoiding the risk of becoming trapped in local minima as might occur when using gradient descent algorithms such as the popular back-propagation. In most cases the convergence of the constructing algorithms is guaranteed by the method used. Constructive methods for building neural networks can potentially create more compact and robust models which are easily implemented in hardware and used for embedded systems. Thus a growing amount of current research in neural networks is oriented towards this important topic. The purpose of this book is to gather together some of the leading investigators and research groups in this growing area, and to provide an overview of the most recent advances in the techniques being developed for constructive neural networks and their applications. |
Contents
1 | |
Efficient Constructive Techniques for Training Switching Neural Networks | 25 |
Constructive Neural Network Algorithms That Solve Highly Nonseparable Problems | 49 |
On Constructing Threshold Networks for Pattern Classification | 71 |
SelfOptimizing Neural Network 3 | 83 |
Multiclass Concept LatticeBased Artificial Neural Network | 102 |
Some Theoretical Aspects and Experimental Results in Classification | 123 |
A Feedforward Constructive Neural Network Algorithm for Multiclass Tasks Based on Linear Separability | 145 |
Active Learning Using a Constructive Neural Network Algorithm | 193 |
Incorporating Expert Advice into Reinforcement Learning Using Constructive Neural Networks | 207 |
A Constructive Neural Network for Evolving a Machine Controller in RealTime | 225 |
Avoiding Prototype Proliferation in Incremental Vector Quantization of Large Heterogeneous Datasets | 243 |
Tuning Parameters in Fuzzy Growing Hierarchical SelfOrganizing Networks | 261 |
Efficient Multiple Classifier System with Pruned SelfGenerating Neural Trees | 281 |
292 | |
Analysis and Testing of themClass RDP Neural Network | 170 |
Other editions - View all
Common terms and phrases
accuracy added approach Artificial Neural Networks axon backpropagation barycenters bipolar binary Boolean functions c3sep CasCor classification problem clusters complete lattice computed concept concept lattices CoNN algorithms connections constructive algorithm constructive neural network data set benchmark dataset defined dendrite Elizondo example feedforward FKCNs FLNN fuzzy GDCs Heidelberg hidden layer hidden neurons hidden node hierarchical hyperboxes hyperplane ICANN input features Iris iterations learning algorithm linear linearly separable LNCS M-CLANN m-class machine learning MBabCoNN misclassified morphological multiclass neural network algorithm number of hidden number of neurons optimal output neuron overfitting parameters perceptron performance procedure projection projection pursuit proposed prototype vectors pruning quantization error reinforcement learning represented reward robot semi-lattice sequential SGNT spiking neural network Springer structure Subnetwork subset task testing threshold decision list threshold network topology training algorithm training data training patterns training set two-class weights wrongly-on