Search results for "Neural Networks"

Highly Performant, Deep Neural Networks with sub-microsecond latency on FPGAs for Trigger Applications

2020

Artificial neural networks are becoming a standard tool for data analysis, but their potential remains yet to be widely used for hardware-level trigger applications. Nowadays, high-end FPGAs, often used in low-level hardware triggers, offer theoretically enough performance to include networks of considerable size. This makes it very promising and rewarding to optimize a neural network implementation for FPGAs in the trigger context. Here an optimized neural network implementation framework is presented, which typically reaches 90 to 100% computational efficiency, requires few extra FPGA resources for data flow and controlling, and allows latencies in the order of 10s to few 100s of nanoseco…

Artificial Neural Networks and Linear Discriminant Analysis:  A Valuable Combination in the Selection of New Antibacterial Compounds

2004

A set of topological descriptors has been used to discriminate between antibacterial and nonantibacterial drugs. Topological descriptors are simple integers calculated from the molecular structure represented in SMILES format. The methods used for antibacterial activity discrimination were linear discriminant analysis (LDA) and artificial neural networks of a multilayer perceptron (MLP) type. The following plot frequency distribution diagrams were used: a function of the number of drugs within a value interval of the discriminant function and the output value of the neural network versus these values. Pharmacological distribution diagrams (PDD) were used as a visualizing technique for the i…

Neural Classification of HEP Experimental Data

2009

High Energy Physics (HEP) experiments require discrimination of a few interesting events among a huge number of background events generated during an experiment. Hierarchical triggering hardware architectures are needed to perform this tasks in real-time. In this paper three neural network models are studied as possible candidate for such systems. A modified Multi-Layer Perception (MLP) architecture and a E alpha Net architecture are compared against a traditional MLP Test error below 25% is archived by all architectures in two different simulation strategies. E alpha Net performance are 1 to 2% better on test error with respect to the other two architectures using the smaller network topol…

Prediction of surface treatment effects on the tribological performance of tool steels using artificial neural networks

2019

The present paper discussed the development of a reliable and robust artificial neural network (ANN) capable of predicting the tribological performance of three highly alloyed tool steel grades. Experimental results were obtained by performing plane-contact sliding tests under non-lubrication conditions on a pin-on-disk tribometer. The specimens were tested both in untreated state with different hardening levels, and after surface treatment of nitrocarburizing. We concluded that wear maps via ANN modeling were a user-friendly approach for the presentation of wear-related information, since they easily permitted the determination of areas under steady-state wear that were appropriate for use…

Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function

2006

This Letter presents a simple and powerful pruning method for multilayer feed forward neural networks based on the fuzzy sigmoid activation function presented in [E. Soria, J. Martin, G. Camps, A. Serrano, J. Calpe, L. Gomez, A low-complexity fuzzy activation function for artificial neural networks, IEEE Trans. Neural Networks 14(6) (2003) 1576-1579]. Successful performance is obtained in standard function approximation and channel equalization problems. Pruning allows to reduce network complexity considerably, achieving a similar performance to that obtained by unpruned networks.

Neural Networks with Multidimensional Cross-Entropy Loss Functions

2019

Deep neural networks have emerged as an effective machine learning tool successfully applied for many tasks, such as misinformation detection, natural language processing, image recognition, machine translation, etc. Neural networks are often applied to binary or multi-class classification problems. In these settings, cross-entropy is used as a loss function for neural network training. In this short note, we propose an extension of the concept of cross-entropy, referred to as multidimensional cross-entropy, and its application as a loss function for classification using neural networks. The presented computational experiments on a benchmark dataset suggest that the proposed approaches may …

Global exponential stability of delayed Markovian jump fuzzy cellular neural networks with generally incomplete transition probability

2014

The problem of global exponential stability in mean square of delayed Markovian jump fuzzy cellular neural networks (DMJFCNNs) with generally uncertain transition rates (GUTRs) is investigated in this paper. In this GUTR neural network model, each transition rate can be completely unknown or only its estimate value is known. This new uncertain model is more general than the existing ones. By constructing suitable Lyapunov functionals, several sufficient conditions on the exponential stability in mean square of its equilibrium solution are derived in terms of linear matrix inequalities (LMIs). Finally, a numerical example is presented to illustrate the effectiveness and efficiency of our res…

Artificial neural networks and liver diseases: An economic and pre-imaging diagnosis

2013

Efficient MLP Digital Implementation on FPGA

2005

The efficiency and the accuracy of a digital feed-forward neural networks must be optimized to obtain both high classification rate and minimum area on chip. In this paper an efficient MLP digital implementation. The key features of the hardware implementation are the virtual neuron based architecture and the use of the sinusoidal activation function for the hidden layer. The effectiveness of the proposed solutions has been evaluated developing different FPGA based neural prototypes for the High Energy Physics domain and the automatic Road Sign Recognition domain. The use of the sinusoidal activation function decreases hardware resource employment of about 32% when compared with the standar…

Short term wind speed prediction using Multi Layer Perceptron

2012

Among renewable energy sources wind energy is having an increasing influence on the supply of energy power. However wind energy is not a stationary power, depending on the fluctuations of the wind, so that is necessary to cope with these fluctuations that may cause problems the electricity grid stability. The ability to predict short-term wind speed and consequent production patterns becomes critical for the all the operators of wind energy. This paper studies several configurations of Artificial Neural Networks (ANN), a well-known tool able to estimate wind speed starting from measured data. The presented ANNs, t have been tested through data gathered in the area of Trapani (Sicily). Diffe…