Due to the large increase of malware samples in the last 10 years, the demand of the antimalware industry for an automated classifier has increased. However, this classifier has to satisfy two restrictions in order to be used in real life situations: high detection rate and very low number of false positives. By modifying the perceptron algorithm and combining existing features, we were able to...

How to reconfigure a logic gate for a variety of functions is an interesting topic. In this paper, a different method of designing logic gates are proposed. Initially, due to the training ability of the multilayer perceptron neural network, it was used to create a new type of logic and full adder gates. In this method, the perceptron network was trained and then tested. This network was 100% ac...

Register value prediction has been proposed as a technique to exploit register value reuse, a form of locality where the result produced by an instruction is the same as the value that is already in a destination register or other registers in the register file. Register value prediction allows increased performance by breaking true dependencies between an instruction that exhibits this localit...

This paper presents a study on classification of blasts in acute leukemia blood samples using artificial neural network. In acute leukemia there are two major forms that are acute myelogenous leukemia (AML) and acute lymphocytic leukemia (ALL). Six morphological features have been extracted from acute leukemia blood images and used as neural network inputs for the classification. Hybrid Multila...

Perceptron branch predictors achieve high prediction accuracy by capturing correlation from very long histories. The required hardware, however, limits the effective history length to be explored, which in turn undermines the potential performance. In this paper, we propose an adaptive approach to dynamically reconfigure the input vector to a perceptron predictor to facilitate correlation explo...

The paper develops a connection between traditional perceptron algorithms and recently introduced herding algorithms. It is shown that both algorithms can be viewed as an application of the perceptron cycling theorem. This connection strengthens some herding results and suggests new (supervised) herding algorithms that, like CRFs or discriminative RBMs, make predictions by conditioning on the i...

This paper proposes a boosting algorithm that uses a semi-Markov perceptron. The training algorithm repeats the training of a semi-Markov model and the update of the weights of training samples. In the boosting, training samples that are incorrectly segmented or labeled have large weights. Such training samples are aggressively learned in the training of the semi-Markov perceptron because the w...

The thermal perceptron is a simple extension to Rosenblatt’s perceptron learning rule for training individual linear threshold units. It finds stable weights for nonseparable problems as well as separable ones. Experiments indicate that if a good initial setting for a temperature parameter, To, has been found, then the thermal perceptron outperforms the Pocket algorithm and methods based on gra...

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 ...

Above figures show that if the solution space only exists at S=1 space and the initial weights are at S = −1 space, the training path needs to pass the origin to change space. It means w3 changes from positive value to negative value. Compare the learning behaviors of two different initial weights, Wa = [1,−2.5, 2] and Wb = 0.5Wa = [0.5,−1.25, 1], we’ll find the bigger absolute value of w3 caus...