HARDWARE PROTOTYPES OF A BOOLEAN NEURAL NETWORK AND THE SIMULATED ANNEALING OPTIMIZATION METHOD

1996 ◽  
Vol 07 (01) ◽  
pp. 45-52
Author(s):  
JARKKO NIITTYLAHTI
Keyword(s):  
Neural Network ◽  
Simulated Annealing ◽  
Logic Gates ◽  
Optimization Method ◽  
General Purpose ◽  
Boolean Logic ◽  
Training Procedure ◽  
The Neural Network ◽  
Neural Network Hardware ◽  
Dynamically Configurable

Boolean Neural Network is a neural network that operates with binary weight values of “1” and “0”. Otherwise it is formally analogous to the Multilayer Perceptron (MLP).1 Simulated Annealing is a stochastic optimization method that is suitable for performing nonlinear multivariable optimization tasks. Training a Boolean Neural Network is a well-suited problem to this algorithm. However, the Simulated Annealing method is computationally heavy, which makes the training procedure slow. The training speed can be improved by using custom designed hardware for the whole system including the optimization method and the neural network. Hardware prototypes of a Boolean Neural Network and the Simulated Annealing optimization method have been designed using discrete components. The Boolean Neural Network implementation is basically a dynamically configurable feedforward network of Boolean logic gates of two inputs. The Simulated Annealing implementation is a general purpose hardware tool for multivariable optimization tasks. Here it is applied to do supervised training of the Boolean Neural Network hardware.

Optimization of Pressure Path in Sheet Hydroforming Process Using Artificial Intelligence and Simulated Annealing

2014 ◽  
Vol 622-623 ◽  
pp. 772-779 ◽  
Author(s):  
Amirreza Yaghoobi ◽  
Mohammad Bakhshi-Jooybari ◽  
Abdolhamid Gorji ◽  
Hamid Baseri
Keyword(s):  
Neural Network ◽  
Finite Element ◽  
Simulated Annealing ◽  
Network Model ◽  
Neural Network Model ◽  
Critical Region ◽  
Element Model ◽  
Sheet Hydroforming ◽  
The Neural Network ◽  
Hydroforming Process

The success of sheet hydroforming process largely depends on the loading pressure path. Pressure path is one of the most important parameters in sheet hydroforming process. In this study, a combination of finite element simulation, artificial intelligence and simulated annealing optimization have been utilized to optimize the pressure path in producing cylindrical-spherical parts. In the beginning, the finite element model was verified based on laboratory experimental results. The experiments were designed and a radial basis neural network model was developed using data generated from verified finite element model to predict the thickness in the critical region of the product. Results indicated that the neural network model could be applied successfully to predict the sheet thickness in the critical region. In addition, the neural network model was used as a fitness function in simulated annealing algorithm to minimize the thickening in the above mentioned critical region. The final results showed that utilization of the optimized pressure path yields good thickness distribution of the part.

Reliability-Based Optimization of Spin-Transfer Torque Magnetic Tunnel Junction Implication Logic Gates

2013 ◽  
Vol 854 ◽  
pp. 89-95 ◽  
Author(s):  
Hiwa Mahmoudi ◽  
T. Windbacher ◽  
V. Sverdlov ◽  
S. Selberherr
Keyword(s):  
Tunnel Junction ◽  
Error Probability ◽  
Magnetic Tunnel Junction ◽  
Logic Gates ◽  
Optimization Method ◽  
Spin Transfer Torque ◽  
Boolean Logic ◽  
Stability Factor ◽  
Gate Circuit ◽  
Reliability Based Optimization

Recently, magnetic tunnel junction (MTJ)-based implication logic gates have been proposed to realize a fundamental Boolean logic operation called material implication (IMP). For given MTJ characteristics, the IMP gate circuit parameters must be optimized to obtain the minimum IMP error probability. In this work we present the optimization method and investigate the effect of MTJ device parameters on the reliability of IMP logic gates. It is shown that the most important MTJ device parameters are the tunnel magnetoresistance (TMR) ratio and the thermal stability factor Δ. The IMP error probability decreases exponentially with increasing TMR and Δ.

Traveltime-table compression using artificial neural networks for Kirchhoff-migration processing of microseismic data

Geophysics ◽  
2020 ◽  
Vol 85 (5) ◽  
pp. U121-U128
Author(s):  
Serafim I. Grubas ◽  
Georgy N. Loginov ◽  
Anton A. Duchkov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Network Architecture ◽  
Training Procedure ◽  
Velocity Models ◽  
Kirchhoff Migration ◽  
Microseismic Data ◽  
The Neural Network ◽  
Artificial Neural

Massive computation of seismic traveltimes is widely used in seismic processing, for example, for the Kirchhoff migration of seismic and microseismic data. Implementation of the Kirchhoff migration operators uses large precomputed traveltime tables (for all sources, receivers, and densely sampled imaging points). We have tested the idea of using artificial neural networks for approximating these traveltime tables. The neural network has to be trained for each velocity model, but then the whole traveltime table can be compressed by several orders of magnitude (up to six orders) to the size of less than 1 MB. This makes it convenient to store, share, and use such approximations for processing large data volumes. We evaluate some aspects of choosing neural-network architecture, training procedure, and optimal hyperparameters. On synthetic tests, we find a reasonably accurate approximation of traveltimes by neural networks for various velocity models. A final synthetic test shows that using the neural-network traveltime approximation results in good accuracy of microseismic event localization (within the grid step) in the 3D case.

Fuzzy Control of a Novel Type of Translational Meshing Motors

2010 ◽  
Vol 121-122 ◽  
pp. 1038-1043
Author(s):  
Wei Wang ◽  
Xin Jian Shan ◽  
Shi Min Wei
Keyword(s):  
Neural Network ◽  
Control System ◽  
Fuzzy Control ◽  
Fuzzy Controller ◽  
Torque Control ◽  
Training Procedure ◽  
Test Results ◽  
Model Reference Control ◽  
The Neural Network ◽  
Control Scheme

Owing to the nonlinear characteristic of a novel type of translational meshing motor with model uncertainties, a model reference control system which consists of a neural network and a fuzzy controller is used. The torque model is identified based on BP neural network, and then Fuzzy controller works as the controller. The description of the control system and training procedure of the neural network are given. The test results obtained for a torque control scheme suitable for the control of the motor are also presented to verify the effectiveness of the proposed nonlinear control scheme. It has been found that the fuzzy control system is able to work reliably.

scholarly journals Nanoscale neural network using non-linear spin-wave interference

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ádám Papp ◽  
Wolfgang Porod ◽  
Gyorgy Csaba
Keyword(s):  
Neural Network ◽  
Spin Wave ◽  
Spin Waves ◽  
Field Pattern ◽  
Small Scale ◽  
Learning Framework ◽  
Wave Interference ◽  
The Neural Network ◽  
Neural Network Hardware ◽  
Signal Routing

AbstractWe demonstrate the design of a neural network hardware, where all neuromorphic computing functions, including signal routing and nonlinear activation are performed by spin-wave propagation and interference. Weights and interconnections of the network are realized by a magnetic-field pattern that is applied on the spin-wave propagating substrate and scatters the spin waves. The interference of the scattered waves creates a mapping between the wave sources and detectors. Training the neural network is equivalent to finding the field pattern that realizes the desired input-output mapping. A custom-built micromagnetic solver, based on the Pytorch machine learning framework, is used to inverse-design the scatterer. We show that the behavior of spin waves transitions from linear to nonlinear interference at high intensities and that its computational power greatly increases in the nonlinear regime. We envision small-scale, compact and low-power neural networks that perform their entire function in the spin-wave domain.

scholarly journals Staring Imaging Real-Time Optimal Control Based on Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Peiyun Li ◽  
Yunfeng Dong ◽  
Hongjue Li
Keyword(s):  
Neural Network ◽  
Optimal Control ◽  
Real Time ◽  
Optimization Method ◽  
Time Optimal Control ◽  
Control Effect ◽  
Neural Network Controller ◽  
The Neural Network ◽  
Time Optimal ◽  
Attitude Controller

In this paper, a real-time optimal attitude controller is designed for staring imaging, and the output command is based on future prediction. First, the mathematical model of staring imaging is established. Then, the structure of the optimal attitude controller is designed. The controller consists of a preprocessing algorithm and a neural network. Constructing the neural network requires training samples generated by optimization. The objective function in the optimization method takes the future control effect into account. The neural network is trained after sample creation to achieve real-time optimal control. Compared with the PID (proportional-integral-derivative) controller with the best combination of parameters, the neural network controller achieves better attitude pointing accuracy and pointing stability.

scholarly journals Assignment of Focus Position with Convolutional Neural Networks in Adaptive Lens Based Axial Scanning for Confocal Microscopy

2022 ◽  
Vol 12 (2) ◽  
pp. 661
Author(s):  
Katharina Schmidt ◽  
Nektarios Koukourakis ◽  
Jürgen W. Czarske
Keyword(s):  
Neural Network ◽  
Applied Voltage ◽  
Laser Scanning ◽  
Degrees Of Freedom ◽  
Single Shot ◽  
Training Procedure ◽  
Focus Position ◽  
The Neural Network ◽  
Complex Adaptive ◽  
Axial Scanning

Adaptive lenses offer axial scanning without mechanical translation and thus are promising to replace mechanical-movement-based axial scanning in microscopy. The scan is accomplished by sweeping the applied voltage. However, the relation between the applied voltage and the resulting axial focus position is not unambiguous. Adaptive lenses suffer from hysteresis effects, and their behaviour depends on environmental conditions. This is especially a hurdle when complex adaptive lenses are used that offer additional functionalities and are controlled with more degrees of freedom. In such case, a common approach is to iterate the voltage and monitor the adaptive lens. Here, we introduce an alternative approach which provides a single shot estimation of the current axial focus position by a convolutional neural network. We use the experimental data of our custom confocal microscope for training and validation. This leads to fast scanning without photo bleaching of the sample and opens the door to automatized and aberration-free smart microscopy. Applications in different types of laser-scanning microscopes are possible. However, maybe the training procedure of the neural network must be adapted for some use cases.

scholarly journals Optimization Analysis Method of New Orthotropic Steel Deck Based on Backpropagation Neural Network-Simulated Annealing Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Xiuli Xu ◽  
Kewei Shi ◽  
Xuehong Li ◽  
Zhijun Li ◽  
Rengui Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Simulated Annealing ◽  
Parameter Optimization ◽  
Design Parameter ◽  
Stress Amplitude ◽  
Optimization Method ◽  
Backpropagation Neural Network ◽  
Orthotropic Steel Deck ◽  
Weighting Coefficients ◽  
Steel Deck

To study the effects of the fatigue performance due to the major design parameter of the orthotropic steel deck and to obtain a better design parameter, a construction parameter optimization method based on a backpropagation neural network (BPNN) and simulated annealing (SA) algorithm was proposed. First, the finite element (FE) model was established, and the numerical results were validated against available full-scale fatigue experimental data. Then, by calculating the influence surface of each fatigue detail, the most unfavorable loading position of each fatigue detail was obtained. After that, combined with the data from actual engineering applications, the weight coefficient of each fatigue detail was calculated by an analytic hierarchy process (AHP). Finally, to minimize the comprehensive stress amplitude, a BPNN and SA algorithm were used to optimize the construction parameters, and the optimization results for the conventional weight coefficients were compared with the construction parameters. It can be concluded that compared with the FE method through single-parameter optimization, the BPNN and SA method can synthetically optimize multiple parameters. In addition, compared with the common weighting coefficients, the weighting coefficients proposed in this paper can be better optimized for vulnerable parts. The optimized fatigue detail stress amplitude is minimized, and the optimization results are reliable. For these reasons, the parameter optimization method presented in this paper can be used for other similar applications.

Letter to the Editor: A DISCRETE-TIME LAGRANGIAN NETWORK FOR SOLVING CONSTRAINED QUADRATIC PROGRAMS

2000 ◽  
Vol 10 (04) ◽  
pp. 261-265 ◽  
Author(s):  
WAI SUM TANG ◽  
JUN WANG
Keyword(s):  
Neural Network ◽  
Discrete Time ◽  
Recurrent Neural Network ◽  
Optimal Solution ◽  
Optimization Method ◽  
Quadratic Program ◽  
Penalty Parameter ◽  
Quadratic Programs ◽  
The Neural Network ◽  
Simulation Results

A discrete-time recurrent neural network which is called the discrete-time Lagrangian network is proposed in this letter for solving convex quadratic programs. It is developed based on the classical Lagrange optimization method and solves quadratic programs without using any penalty parameter. The condition for the neural network to globally converge to the optimal solution of the quadratic program is given. Simulation results are presented to illustrate its performance.

Data-Based Approach to Optimizing the Ocean Wave Energy Carpet Using Deep Neural Network

2020 ◽  
Author(s):  
Ninh Hai Do ◽  
Mohammad-Reza Alam
Keyword(s):  
Neural Network ◽  
Wave Energy ◽  
Optimization Problems ◽  
Optimization Method ◽  
Sequential Optimization ◽  
Single Frequency ◽  
Data Set ◽  
Ocean Wave Energy ◽  
The Neural Network ◽  
Computationally Expensive

Abstract In this paper, we present the Neural Network-based Optimization Method, applied to optimizing the wave energy converter “wave carpet”. The proposed method can be applied to optimizing the computationally expensive objective function that other sequential optimization approaches fail to do. The results show that, in the simple case of single-frequency unidirectional incoming waves, this optimization method achieves the optimal carpet shape that can absorb 2.18 times more energy than the baseline circular shape, and in its best performance the neural network can optimize the carpet shape that absorbs 7 times more energy than the baseline, after being trained on a medium data set. Thus, the proposed method can be considered an effective approach to solving the optimization problems involving computationally expensive objective functions.

Sign in / Sign up

Export Citation Format

Share Document