It is well known that a two-layer perceptron network with threshold neurons is incapable of forming arbitrary decision regions in input space, while a three-layer perceptron has that capability. The effect of replacing the output neuron in a two-layer perceptron with a bithreshold element is studied. The limitations of this modified two-layer perceptron are observed. Results on the separating c...

In this paper, a new Transform Domain implementation of the well known Multilayer Perceptron Neural Network is presented. With the Transform Domain implementation, the input of the Neural Network can be represented in a more compact manner and the elements of the input vector become uncorrelated. The new Transform Domain Multilayer Perceptron (TDMLP) Neural Network is applied for the problem of...

The classical perceptron rule provides a varying upper bound on the maximum margin, namely the length of the current weight vector divided by the total number of updates up to that time. Requiring that the perceptron updates its internal state whenever the normalized margin of a pattern is found not to exceed a certain fraction of this dynamic upper bound we construct a new approximate maximum ...

Perceptron branch predictors achieve high prediction accuracy by capturing correlation from very long histories. The required hardware, however, limits the history length to be explored practically. In this paper, an important observation is made that the perceptron weights can be used to estimate the strength of branch correlation. Based such an estimate, adaptive schemes are proposed to prepr...

We give an adversary strategy that forces the Perceptron algorithm to make a( kN) mistakes in learning monotone disjunctions over N variables with at most k literals. In contrast, Littlestone’s algorithm Winnow makes at most 0( k log N) mistakes for the same problem. Both algorithms use thresholded linear functions as their hypotheses. However, Winnow does multiplicative updates to its weight v...

In this paper, we propose a combined method for hand shape recognition. It consists of support vector machines (SVMs) and an online learning algorithm based on the perceptron. We apply HOG features to each method. First, our method estimates a hand shape of an input image by using SVMs. Here the online learning method with the perceptron uses the input image as new training data if the data is ...

Online learning algorithms like the perceptron are widely used for structured prediction tasks. For sequential search problems, like left-to-right tagging and parsing, beam search has been successfully combined with perceptron variants that accommodate search errors (Collins and Roark, 2004; Huang et al., 2012). However, perceptron training with inexact search is less studied for bottom-up pars...

This paper presents a fuzzy perceptron as a generic model of multilayer fuzzy neural networks, or neural fuzzy systems, respectively. This model is suggested to ease the comparision of diierent neuro{fuzzy approaches that are known from the literature. A fuzzy perceptron is not a fuzziication of a common neural network architecture, and it is not our intention to enhance neural learning algorit...

Memristors are low-power memory-holding resistors thought to be useful for neuromophic computing, which can compute via spike-interactions mediated through the device’s short-term memory. Using interacting spikes, it is possible to build an AND gate that computes OR at the same time, similarly a full adder can be built that computes the arithmetical sum of its inputs. Here we show how these gat...