We analyze and compare the well-known gradient descent algorithm and the more recent
exponentiated gradient algorithm for training a single neuron with an arbitrary transfer …

This paper proposes a novel supervised learning method for single-layer feedforward neural
networks. This approach uses an alternative objective function to that based on the MSE …

The article presents a method for learning the weights in one-layer feed-forward neural
networks minimizing either the sum of squared errors or the maximum absolute error …

In the scope of data analytics, the volume of a data set can be defined as a product of
instance size and dimensionality of the data. In many real problems, data sets are mainly …

One‐class classification has gained interest as a solution to certain kinds of problems typical
in a wide variety of real environments like anomaly or novelty detection. Autoencoder is the …

In machine learning literature, and especially in the literature referring to artificial neural
networks, most methods are iterative and operate in batch mode. However, many of the …

In this paper the geometric formulation of the single layer perceptron weight optimization
problem previously described by Coetzee et al.(1993, 1996) is combined with results from …

The author extends the geometrical approach to the perceptron and shows that, given n
examples, learning is of maximal difficulty when the number of inputs d is such that n= 5d …

In his seminal paper Cover (1965) used geometrical arguments to compute the probability of
separating two sets of patterns with a perceptron. The authors extend these ideas to …

A fully connected recurrent network that is capable of storing, recalling, and generating a
pattern sequence, is presented. This network reproduces a memorized sequence by …