In order to shorten the fussy experimental process in heat treatment of 7003 aluminum alloy, back-propagation(BP) artificial neural network control of scheme has been proposed. The network of arithmetic has been deduc...
详细信息
In order to shorten the fussy experimental process in heat treatment of 7003 aluminum alloy, back-propagation(BP) artificial neural network control of scheme has been proposed. The network of arithmetic has been deduced by using gradient descent algorithms. A BP neural network has been established between the heat treatment technique and the hardness. The results indicated that the predicted results are closed to the test results. The weakness that the nonlinear and time variation relationship between heat treatment and the hardness could be approached more accurately, effectively by using single-factor-experiment method has been overcome. Hence providing a effective, economical,rapid way for the heat treatment optimization of nonferrous metals and ferrous metal.
A nonlinear gradientdescent (NGD) learning algorithm with an adaptive amplitude of the nonlinearity is derived for the class of nonlinear finite impulse response (FIR) adaptive filters (dynamical perceptron). This is...
详细信息
A nonlinear gradientdescent (NGD) learning algorithm with an adaptive amplitude of the nonlinearity is derived for the class of nonlinear finite impulse response (FIR) adaptive filters (dynamical perceptron). This is based on the adaptive amplitude backpropagation (AABP) algorithm for large-scale neural networks. The amplitude of the nonlinear activation function is made gradient adaptive to give the adaptive amplitude nonlinear gradientdescent (AANGD) algorithm, making the AANGD suitable for processing nonlinear and nonstationary input signals with a large dynamical range. Experimental results show the AANGD algorithm outperforming the standard NGD algorithm on both colored and nonlinear input with large dynamics. Despite its simplicity, the considered algorithm proves suitable for adaptive filtering of nonlinear and nonstationary signals.
In this paper, we propose a frequency-domain method employing robust independent component analysis (RICA) to address the multichannel Blind Source Separation (BSS) problem of convolutive speech mixtures in highly rev...
详细信息
In this paper, we propose a frequency-domain method employing robust independent component analysis (RICA) to address the multichannel Blind Source Separation (BSS) problem of convolutive speech mixtures in highly reverberant environments. We impose regularization processes to tackle the ill-conditioning problem of the covariance matrix and to mitigate the performance degradation. We evaluate the impact of several parameters on the performance of separation, e.g., windowing type and overlapping ratio of the frequency domain method. We then assess and compare different techniques to solve the frequency-domain permutation ambiguity. Furthermore, we develop an algorithm to separate the source signals in adverse conditions, i.e. high reverberation conditions when short observation signals are available. Finally, through extensive simulations and real-world experiments, we evaluate and demonstrate the superiority of the presented convolutive algorithmic system in comparison to other BSS algorithms, including recursive regularized ICA (RR-ICA) and independent vector analysis (IVA).
A novel stochastic gradient algorithm for finite impulse response (FIR) adaptive filters, termed the least sum of exponentials (LSE), is introduced. In order to provide a generalisation of the class of weighted mixed ...
详细信息
ISBN:
(纸本)9781424408818
A novel stochastic gradient algorithm for finite impulse response (FIR) adaptive filters, termed the least sum of exponentials (LSE), is introduced. In order to provide a generalisation of the class of weighted mixed norm algorithms and at the same time avoid problems associated with a large number of free parameters of such algorithms, LSE is derived by minimising a sum of error exponentials. A rigourous mathematical analysis is provided, resulting in closed form expressions for the optimal weights and the upper bound of the learning rate. The analysis is supported by simulations in a system identification setting.
In a bid to predict the propagation loss of electromagnetic signals, different models based on empirical and deterministic formulas have been used. In this study, different artificial neural network models which are v...
详细信息
ISBN:
(纸本)9781509064229
In a bid to predict the propagation loss of electromagnetic signals, different models based on empirical and deterministic formulas have been used. In this study, different artificial neural network models which are very effective for prediction were used for the prediction of signal power loss in a microcell environment, Obio-Akpor, Port Harcourt, Nigeria. The signal power loss of the area is studied based on three artificial neural network algorithms with nine training functions. For the training of the artificial neural network, the input data were the distance from the transmitter and the signal power loss. Training of neural network is a demanding task in the field of supervised learning research. This is because the main difficulty in adopting artificial neural network is in finding the most suitable combination of learning and training functions for the prediction task. We compared the performance of three training algorithms in feedforward back propagation multi layer perceptron neural network. Nine training functions under three training algorithms were selected: the gradientdescent based algorithms, the Conjugate gradient based algorithms and the Quasi-Newton based algorithms. The work compared the training algorithms on the basis of mean square error, mean absolute error, standard deviation, correlation coefficient, regression on training and validation and the rate of convergence. The general performance of the training functions demonstrates their effectiveness to yield accurate results in short time. The conclusion on the training functions is based on the simulation results using measurement data from the micro environment.
Herein, dual-gate field-effect transistors (DG FETs) fabricated on Si substrate and a corresponding NOR-type array designed for low-power on-chip trainable hardware neural networks (HNNs) are presented. The fabricated...
详细信息
Herein, dual-gate field-effect transistors (DG FETs) fabricated on Si substrate and a corresponding NOR-type array designed for low-power on-chip trainable hardware neural networks (HNNs) are presented. The fabricated DG FET exhibits notable endurance characteristics, with the subthreshold swing remaining consistently within a 2.45% range of change and Delta Vth per cycle maintaining stability at 4.5% over repetitive program and erase operations, up to 104 cycles. Furthermore, a multilevel characteristic is achieved through low-power program/erase operations based on Fowler-Nordheim (FN) tunneling, which exhibit 0.09 and 0.99 fJ per spike, respectively. These characteristics provide the HNN stability, along with high performance and power efficiency. The NOR-type array in this work demonstrates selective update and bidirectional vector-by-matrix multiplication capabilities. This enables on-chip training based on a gradientdescent algorithm, without the need for an additional array for backpropagation. Subsequently, a simulation of the Modified National Institute of Standards and Technology classification is conducted to evaluate the accuracy and training power consumption of the proposed device in comparison to other two-terminal memristor devices. The results show that the DG FET array achieves superior accuracy while maintaining over 180.4 times higher energy efficiency, demonstrating the potential of the DG FET as a promising candidate for low-power HNN applications. Herein, dual-gate field-effect transistors (DG FETs) for low-power on-chip hardware neural networks (HNNs) are reported. The saturation characteristic of the device provides robustness against voltage fluctuations. The NOR-type DG FET array is capable of both bidirectional operation and selective updates based on Fowler-Nordheim tunneling, reducing the latency and power consumption during the training phase of the on-chip trainable *** (c) 2023 WILEY-VCH GmbH
This paper studies the problem of letting an autonomous mobile robot negotiate obstacles in an optimal manner. In particular, a multi-modal control problem is addressed, where different modes of operation control the ...
详细信息
This paper studies the problem of letting an autonomous mobile robot negotiate obstacles in an optimal manner. In particular, a multi-modal control problem is addressed, where different modes of operation control the robot at different locations in the state space. The specification of the optimal discrete event dynamics is pursued through the design of optimal, parametrized switching surfaces, using results on switching surface optimization.
暂无评论