scholarly journals An Optimal Implementation on FPGA of a Hopfield Neural Network

2011 ◽  
Vol 2011 ◽  
pp. 1-9 ◽  
Author(s):  
W. Mansour ◽  
R. Ayoubi ◽  
H. Ziade ◽  
R. Velazco ◽  
W. EL Falou
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
High Performance ◽  
Optimization Problems ◽  
Parallel Architecture ◽  
Hopfield Neural Network ◽  
Noise Removal ◽  
Combinatorial Optimization Problems ◽  
Artificial Neural Network Ann ◽  
Optimal Implementation

The associative Hopfield memory is a form of recurrent Artificial Neural Network (ANN) that can be used in applications such as pattern recognition, noise removal, information retrieval, and combinatorial optimization problems. This paper presents the implementation of the Hopfield Neural Network (HNN) parallel architecture on a SRAM-based FPGA. The main advantage of the proposed implementation is its high performance and cost effectiveness: it requires O(1) multiplications and O(log⁡ N) additions, whereas most others require O(N) multiplications and O(N) additions.

scholarly journals Artificial neural network for solving multi-parameter optimization problems

2021 ◽  
Vol 2092 (1) ◽  
pp. 012013
Author(s):  
Krivorotko Olga ◽  
Liu Shuang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Optimization Problems ◽  
Three Dimensional ◽  
Test Functions ◽  
Backpropagation Method ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Quality Of Approximation ◽  
And Function

Abstract An artificial neural network (ANN) is a mathematical or computational model that simulates the structure and function of biological neural networks used to evaluate or approximate functions at given points. After developing the training algorithm, the resulting model will be used to solve image recognition problems, control problems, optimization, etc. In the process of ANN training, the algorithm of backpropagation is used in the case of convex optimization functions. The article is analyzed test functions for experiments and also study the effect of the number of ANN layers on the quality of approximation in cases one-, two- and three-dimensional. The backpropagation method is improved during the experiments with the help of adaptive gradient, as a result of which more accurate approximations of the functions are obtained. This article also presents the numerical results of test functions.

Evaluation of the Use of Artificial Neural Networks in Solar Energy

2021 ◽  
pp. 182-210
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Set Theory ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Pv System ◽  
Solar Insolation ◽  
Pv Panel ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Artificial neural network (ANN) is initially used to forecast the solar insolation level and followed by the particle swarm optimisation (PSO) to optimise the power generation of the PV system based on the solar insolation level, cell temperature, efficiency of PV panel, and output voltage requirements. Genetic algorithm is a general-purpose optimization algorithm that is distinguished from conventional optimization techniques by the use of concepts of population genetics to guide the optimization search. Tabu search algorithm is a conceptually simple and an elegant iterative technique for finding good solutions to optimization problems. Simulated annealing algorithms appeared as a promising heuristic algorithm for handling the combinatorial optimization problems. Fuzzy logic algorithms set theory can be considered as a generation of the classical set theory. The artificial neural network (ANN)-based solar insolation forecast has shown satisfactory results with minimal error, and the generated PV power can be optimised significantly with the aids of the PSO algorithm.

Neuromodeling and Natural Optimization of Nonlinear Devices and Circuits

2011 ◽  
pp. 326-348 ◽  
Author(s):  
Paulo H. da F. Silva ◽  
Rossana M. S. Cruz ◽  
Adaildo G. D’Assunção
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Optimization Problems ◽  
Optimization Algorithms ◽  
Electromagnetic Modeling ◽  
Neural Network Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Nonlinear Devices

This chapter describes some/new artificial neural network (ANN) neuromodeling techniques and natural optimization algorithms for electromagnetic modeling and optimization of nonlinear devices and circuits. Neuromodeling techniques presented are based on single hidden layer feedforward neural network configurations, which are trained by the resilient back-propagation algorithm to solve the modeling learning tasks associated with device or circuit under analysis. Modular configurations of these feedforward networks and optimal neural networks are also presented considering new activation functions for artificial neurons. In addition, some natural optimization algorithms are described, such as continuous genetic algorithm (GA), a proposed improved-GA and particle swarm optimization (PSO). These natural optimization algorithms are blended with multilayer perceptrons (MLP) artificial neural network models for fast and accurate resolution of optimization problems. Some examples of applications are presented and include nonlinear RF/microwave devices and circuits, such as transistors, filters and antennas.

scholarly journals Artificial Neural Network in Fibres Length Prediction for High Precision Control of Cellulose Refining

Materials ◽  
2019 ◽  
Vol 12 (22) ◽  
pp. 3730 ◽  
Author(s):  
Daniele Almonti ◽  
Gabriele Baiocco ◽  
Vincenzo Tagliaferri ◽  
Nadia Ucciardello
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
High Performance ◽  
Refining Process ◽  
Cellulose Fibres ◽  
Structures And Properties ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Base Substrate ◽  
Broad Possibility

Paper, a web of interconnected cellulose fibres, is widely used as a base substrate. It has been applied in several applications since it features interesting properties, such as renewability, biodegradability, recyclability, affordability and mechanical flexibility. Furthermore, it offers a broad possibility to modify its surface properties toward specifics additives. The fillers retention and the fibres bonding ability are heavily affected by the cellulose refining process that influences chemical and morphological features of the fibres. Several refining theories were developed in order to determine the best refining conditions. However, it is not trivial to control the cellulose refining as different phenomena occur simultaneously. Therefore, it is intuitively managed by experienced papermakers to improve paper structures and properties. An approach based on the machine learning aimed at estimating the effects of refining on the fibres morphology is proposed in this study. In particular, an artificial neural network (ANN) was implemented and trained with experimental data to predict the fibres length as a function of refining process variables. The prediction of this parameter is crucial to obtain a high-performance process in terms of effectiveness and the optimisation of the final product performance as a function of the process parameter. To achieve these results, data mining of the experimental patterns collected was exploited. It led to the achievement of excellent performance and high accuracy in fibres length prediction.

scholarly journals An efficient quantum multiverse optimization algorithm for solving optimization problems

2020 ◽  
Vol 9 (1) ◽  
pp. 27
Author(s):  
Samira Sarvari ◽  
Nor Fazlida Mohd. Sani ◽  
Zurina Mohd Hanapi ◽  
Mohd Taufik Abdullah
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Intrusion Detection System ◽  
Quantum Interference ◽  
Optimization Problems ◽  
Detection System ◽  
Optimal Solution ◽  
The Neural Network ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

<p>Due to the recent trend of technologies to use the network-based systems, detecting them from threats become a crucial issue. Detecting unknown or modified attacks is one of the recent challenges in the field of intrusion detection system (IDS). In this research, a new algorithm called quantum multiverse optimization (QMVO) is investigated and combined with an artificial neural network (ANN) to develop advanced detection approaches for an IDS. QMVO algorithm depends on adopting a quantum representation of the quantum interference and operators in the multiverse optimization to obtain the optimal solution. The QMVO algorithm determining the neural network weights based on the kernel function, which can improve the accuracy and then optimize the training part of the artificial neural network. It is demonstrated 99.98% accuracy with experimental results that the proposed QMVO is significantly improved optimization compared with multiverse optimizer (MVO) algorithms.</p>

scholarly journals Combinatorial optimization by weight annealing in memristive hopfield networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Z. Fahimi ◽  
M. R. Mahmoodi ◽  
H. Nili ◽  
Valentin Polishchuk ◽  
D. B. Strukov
Keyword(s):  
Neural Network ◽  
Combinatorial Optimization ◽  
Optimization Problems ◽  
Main Idea ◽  
Hopfield Neural Network ◽  
Combinatorial Problems ◽  
Hopfield Network ◽  
Global Minima ◽  
Mixed Signal ◽  
Combinatorial Optimization Problems

AbstractThe increasing utility of specialized circuits and growing applications of optimization call for the development of efficient hardware accelerator for solving optimization problems. Hopfield neural network is a promising approach for solving combinatorial optimization problems due to the recent demonstrations of efficient mixed-signal implementation based on emerging non-volatile memory devices. Such mixed-signal accelerators also enable very efficient implementation of various annealing techniques, which are essential for finding optimal solutions. Here we propose a “weight annealing” approach, whose main idea is to ease convergence to the global minima by keeping the network close to its ground state. This is achieved by initially setting all synaptic weights to zero, thus ensuring a quick transition of the Hopfield network to its trivial global minima state and then gradually introducing weights during the annealing process. The extensive numerical simulations show that our approach leads to a better, on average, solutions for several representative combinatorial problems compared to prior Hopfield neural network solvers with chaotic or stochastic annealing. As a proof of concept, a 13-node graph partitioning problem and a 7-node maximum-weight independent set problem are solved experimentally using mixed-signal circuits based on, correspondingly, a 20 × 20 analog-grade TiO2 memristive crossbar and a 12 × 10 eFlash memory array.

Literature Review

2018 ◽  
pp. 67-80
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Particle Swarm Optimization ◽  
Literature Review ◽  
Noise Removal ◽  
Swarm Optimization ◽  
Artificial Neural Network Ann ◽  
Intelligent Methods ◽  
Short Explanation

This chapter introduces different resources about noise in heart signals. It also provides a short explanation about artificial neural network (ANN), particle swarm optimization (PSO), and presents some of the previous studies related to heart signal noise removal, intelligent methods for detection of disorders, and feature extraction.

Sign in / Sign up

Export Citation Format

Share Document