Machine learning, neural and statistical classification | Guide books skip to main content ACM
Digital Library home ACM Association for Computing Machinery corporate logo Google, Inc …

Neural network methods have proven to be powerful tools in modelling of nonlinear
processes. One crucial part of modelling is the training phase where the model parameters …

We present DESTRUCT, a new method of protein secondary structure prediction, which
achieves a three‐state accuracy (Q3) of 79.4% in a cross‐validated trial on a nonredundant …

Multi-layer networks of threshold logic units (TLU) offer an attractive framework for the
design of pattern classification systems. A new constructive neural network learning …

A constructive algorithm is presented which combines the architecture of Cascade
Correlation and the training of perceptron-like hidden units with the specific error-correcting …

Recent theoretical results support that decreasing the number of free parameters in a neural
network (ie, weights) can improve generalization. These results have triggered the …

In order to find an appropriate architecture for a large-scale real-world application
automatically and efficiently, a natural method is to divide the original problem into a set of …

Massively parallel networks of relatively simple computing elements offer an attractive and
versatile framework for exploring a variety of learning structures and processes for intelligent …

An important research problem in constructive network algorithms is how to train the new
network after the addition of a hidden unit. Some previous empirical analyses performed on …

Abstract Back-propagation (BP)[9, 5] is one of the most widely used procedures for training
multi-layer artificial neural networks with sigmoid units. Though successful in a number of …