Training a perceptron by a bit sequence: storage capacity

J ul 1 99 6 Training a perceptron by a bit sequence : Storage capacity

A perceptron is trained by a random bit sequence. In comparison to the corresponding classification problem, the storage capacity decreases to α c = 1.70±0.02 due to correlations between input and output bits. The numerical results are supported by a signal to noise analysis of Hebbian weights.

Storage capacity of the reversed wedge perceptron with binary connections

Storage of correlated patterns in a perceptron

We calculate the storage capacity of a perceptron for correlated Gaussian patterns. We find that the storage capacity αc can be less than 2 if similar patterns are mapped onto different outputs and vice versa. As long as the patterns are in a general position we obtain, in contrast to previous works, that αc ≥ 1 in agreement with Cover’s theorem. Numerical simulations confirm the results. The c...

Multilayer Perceptron Training

In this contribution we present an algorithm for using possibly inaccurate knowledge of model derivatives as a part of the training data for a multilayer perceptron network (MLP). In many practical process control problems there are many well-known rules about the eeect of control variables to the target variables. With the presented algorithm the basically data driven neural network model can ...

Training a perceptron in a discrete weight space.

Learning in a perceptron having a discrete weight space, where each weight can take 2L+1 different values, is examined analytically and numerically. The learning algorithm is based on the training of the continuous perceptron and prediction following the clipped weights. The learning is described by a new set of order parameters, composed of the overlaps between the teacher and the continuous/c...