Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast
learning of neural networks. Families of parameterized transfer functions provide flexible …

The choice of transfer functions may strongly influence complexity and performance of
neural networks. Although sigmoidal transfer functions are the most common there is no a …

Standard feedforward neural networks benefit from the nice theoretical properties of
mixtures of sigmoid activation functions, but they may fail in several practical learning tasks …

Adaptive systems of the Artificial Neural Network (ANN) type (Haykin, 1994) were initially
motivated by the parallel-processing capabilities of the real brain, but the processing …

In the field of neural network research a number of spectacular experiments are described,
which seem to be in contradiction with the classical pattern recognition or statistical …

In neural networks literature, there is a strong interest in identifying and defining activation
functions which can improve neural network performance. In recent years there has been a …

Fundamentals of Machine Learning | SpringerLink Skip to main content Advertisement
SpringerLink Account Menu Find a journal Publish with us Track your research Search Cart …

Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
Page 1 Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two …

An overview of feedforward networks with one hidden layer with Ra-dial Basis Function
(RBF) units is presented. The learning process of this type of network can take advantage of …

For a variety of reasons, the relative impacts of neural-net inputs on the output of a network's
computation is valuable information to obtain. In particular, it is desirable to identify the …