人工神经网络的模型、特征及其发展方向

人工神经网络的研究越来越受到人们的关注，其理论、方法和应用的研究获得了大量的成果。本文介绍了人工神经网络的基本模型及特性，简要地概括了神经网络的发展方向。     

人工神经网络在激光加工温度场模拟中的应用

研究了人工神经网络在激光加工温度场模拟用的参数推算中的应用方法；并设计了相应的BP神经网络模型及软件；研究表明BP神经网络适用于对激光加工模拟的参数推算，其准确性优于回归分析法和函数插值法。     

深熔激光焊焊缝形状人工神经网络模型和混合专家系统

介绍了利用人工神经网络建立深溶激光焊焊缝形状模型和基于人工神经网络的混合专家系统模型。以Ｎｄ：ＹＡＧ激光焊接Ｍｏｎｅｌ４００的实例介绍了应用ＡＮＮ模型研究激光焊接规范参数和焊缝形状的关系,并提出了基于ＡＮＮ的焊接规范参数优化方法。结果显示,模型具有很好性能。     

人工神经网络的基本原理及其在通信中的应用

人工神经网络是模型生物信息处理系统而建立起来的信息处理模式，是当前国际上研究的热点。由于神经网络具有自适应学习，大规模并行处理与分布式存储，非线性变换，联想记忆等功能，使其在许多方面拥有优于计算机的性能。本文介绍了神经网络的基本概念及具有代表性的模型，着重给出了其在现代通信领域内的应用实例及方法。     

PCNN的原理及其应用

本文综述了一种新的有生物学依据的人工神经网络－脉冲藕合神经网络（PCNN－Pulse Coupled Neural Networks)的模型与原理,同时分析并总结了其特性与其在图象处理,图象识别,运动目标识别,通讯,决策优化等方面的应用,并指出了今后PCNN的研究重点。     

基于人工神经网络的长江水质评价模型

为了能够客观地对长江水质进行评价,在分析人工神经网络原理的基础上,通过对水质污染指标浓度生成样本的方法,生成了适用于人工神经网络模型训练的样本,并应用基于误差反向传播原理的前向多层神经网络,建立了用于长江水质评价的人工神经网络模型。将该模型用于长江水环境评价,通过模型的计算,得到长江水质类别。评价结果表明该模型设计合理、泛化能力强,对长江水质评价具有较好的客观性、通用性和实用性。     

量子神经网络及其应用

量子计算与人工神经网络相结合的量子神经网络(Quantum Neural Networks,QNN)有可能成为未来信息处理的重要手段。分析了人工神经网络向QNN演变的动因及形式、QNN的优势及可能的物理实现方法。着重讨论了几种QNN模型的结构、学习方法及特性,并阐述了QNN在模式识别、纠缠计算、函数近似等方面的初步应用。     

人式神经网络的发展及其潜在应用

文章着重介绍人工神经网络的发展历史与潜在应用，力图从实际应用的角度使人们更好地了解并展开对人工神经网络的研究。     

基于人工神经网络模型优化的研究及应用

人工神经网络在互联网技术和多媒体技术的不断推动作用下,已经广泛应用在很多不同地领域。在该研究当中主要介绍了人工神经网络的主要特点与基本原理,同时还分析了两种不同的模型,最后再分析模型在具体领域当中的应用方法,帮助解决实际存在的问题。     

探究AI大模型：现状、挑战与未来

文章简要介绍AI（人工智能）大模型的定义和重要性，以及人工神经网络结构和深度学习历史。探讨了AI大模型在语言处理、图像识别和推荐系统等任务中的应用。讨论训练AI大模型的原理、数据重要性、硬件要求和分布式训练技术。探寻AI大模型在可解释性挑战、长期记忆与推理以及非监督学习方面的进展。提出对AI大模型的普适性理解和未来发展的展望。     

Nonintrusive appliance load monitoring

A nonintrusive appliance load monitor that determines the energy consumption of individual appliances turning on and off in an electric load, based on detailed analysis of the current and voltage of the total load, as measured at the interface to the power source is described. The theory and current practice of nonintrusive appliance load monitoring are discussed, including goals, applications, load models, appliance signatures, algorithms, prototypes field-test results, current research directions, and the advantages and disadvantages of this approach relative to intrusive monitoring     

The forward EEG solutions can be computed using artificial neural networks

Study of electroencenphalography (EEG) is the one of the most utilized methods in both basic brain research and clinical diagnosis of neurological disorders. Recent technological advances in computer and electronic systems have allowed the EEG to be recorded from large electrode arrays. Modeling the brain waves using a head volume conductor model provides an effective method to localize functional generators within the brain. However, the forward solutions to this model, which represent theoretical potentials in response to current sources within the volume conductor, are difficult to compute because of time-consuming numerical procedures utilized in either the boundary element method (BEM) or the finite element method (FEM). This paper presents a novel computational approach using an artificial neural network (ANN) to map two vectors of forward solutions. These two vectors correspond to different head models but with respect to the same current source. The input vector to the ANN is based on the spherical head model, which can be computed efficiently but involves large errors. The output vector from the ANN is based on the spheroidal model, which is more precise, but difficult to compute directly using the traditional means. Our experiments indicate that this ANN approach provides a remarkable improvement over the BEM and FEM methods: 1) the mean-square error of computation was only approximately 0.3% compared to the exact solution; 2) the online computation was extremely efficient, requiring only 168 floating point operations per channel to compute the forward solution, and 10.2 K-bytes of storage to represent the entire ANN. Using this approach it is possible to perform real-time EEG modeling accurately on personal computers.     

Neural Network Models for Finline Discontinuities

The radial basis network is used as the finline discontinuities electromagnetic artifical neural network(EM‐ANN) models. EM software analysis is employed to characterize finline discontinuities. EM‐ANN models are then trained using physical parameters and frequency as inputs and equivalent electric circuit element parameters of finline discontinuities as outputs. Once trained , the EM‐ANN models can simulate equivalent electric circuit element parameters of finline step, notch and strip very fast and efficiently.     

An analogue test technique for massively parallel integrated circuits and systems: An approach to neural networks circuits testing

The increase in integration density and in complexity of moderns integrated circuits and systems revealed the necessity to consider the testability problem at the design level of circuits. One of the most active research areas in circuits design, over the past decade, has been the implementation of neural networks as electronic VLSI chips. Especially, the implementation of artificial neural networks (ANN) as CMOS integrated circuits shows several attractive features. Recent studies point out that classification is their most successful application field, and thus large networks will be required. Unfortunately, very few papers analyse the testability of electronic implementation of artificial neural networks. A large number of artificial neural networks models deal with binary output neurones. This paper presents and discuss a global current measurement based pseudo-analogue technique for digital-output electronic neural networks testing. Two approaches have been presented and their limitations have been discussed. Simulation results and a method validation test circuit have been presented.     

Remote sensing of forest change using artificial neural networks

A prolonged drought in the Lake Tahoe Basin in California has resulted in extensive conifer mortality. This phenomenon can be analyzed using (multitemporal) remote sensing data. Prior research in the same region used more traditional methods of change detection. The present paper introduces a third approach to change detection in remote sensing based on artificial neural networks. The neural network architecture used is a multilayer feedforward network. The results of the study indicate that the artificial neural network (ANN) estimates conifer mortality more accurately than the other approaches. Further, an analysis of its architecture reveals that it uses identifiable scene characteristics-the same as those used by a Gramm-Schmidt transformation. ANN models offer a viable alternative for change detection in remote sensing     

Simple model for quantum-dot semiconductor optical amplifiers using artificial neural networks

A simple, accurate, and fast multilayer feedforward artificial neural network (ANN) model for quantum-dot semiconductor optical amplifiers (QD-SOAs) is developed. The developed ANN model has demonstrated excellent precision and accurately models the physical characteristics of QD-SOAs such as pulse amplification and four-wave mixing characteristics. Furthermore, the developed ANN model requires a very small computational time compared with numerical models, which is very attractive for computer-aided-design applications. The model is used to create very interesting design curves for QD-SOAs. In addition, the model is suitable for physical-parameter extraction from available measured data.     

Design of broadband array elements based on neural network and genetic algorithm

Coupled artificial neural network (ANN) and genetic algorithm (GA) models are developed for the design of broadband tapered slot antenna array elements. The ANN is employed to establish the complicated relationships between the key array performance indicator, i.e. active reflection coefficient, and its element parameters. The trained ANN models are combined with the GA to optimise the element parameters for a given operating frequency band without using time-consuming EM simulators. Optimisation results show the developed ANN-GA model can retain the accuracy obtainable from EM simulators and exhibit high computational efficiency.     

基于神经网络的光纤温度和应变快速解调方法

为了提高基于布里渊散射的分布式光纤传感系统实时性,在分析经典基于洛伦兹和伪Voigt模型拟合法优缺点的基础上,将多层前馈神经网络方法用于布里渊频移的估算.确定了神经网络的结构、输入及输出量、激活函数和训练算法,采用不同信噪比(5dB～40dB)和布里渊频移(10.62GHz～10.82GHz)的布里渊谱训练该网络,训练...     

GSM Mobile Station Location Using Reference Stations and Artificial Neural Networks

In this paper we present a novel approach to the automatic GSM mobile station location. The approach is based on measurement of radio signal strengths from a number of the neighboring base stations (antennas) and estimation of the mobile station position using trained artificial neural network (ANN) models. First, we present an improved version of our previous positioning back propagation (BP) ANN multi-level perceptron (MLP) model that further improves positioning accuracy. Then, we extend the MLP primary ANN model by introducing correctional factors obtained from a number of reference stations with known positions. Two new models with the improved location accuracy, both aimed at real-time application, are presented. The first model is using differential range to improve the estimated location of the mobile station. The second is using small-scale secondary neural networks trained with data obtained from reference stations, in addition to the primary ANN, to correct location accuracy.     

Cycle life estimation of lithium-ion polymer batteries using artificial neural network and support vector machine with time-resolved thermography

A battery cycle life forecast method without requirements of contact measurement devices and long testing time would be beneficial for industrial applications. The combination of infrared thermography and supervised learning techniques provided the potential solution to this problem. This research investigates the application of machine learning techniques—artificial neural networks (ANNs) and support vector machines (SVMs)—in combination with thermography for cycle life estimation of lithium-ion polymer batteries. Infrared images were captured at 1 frame/min during 70 min of charging followed by 60 min of discharging for 410 cycles. The surface temperature profiles during either charging or discharging were used as the input nodes for ANN and SVM models. The results demonstrated that with thermal profiles as the input, ANN could estimate the current cycle life of studied cell with the error of < 10% under 10 min of testing time. While when compared to ANN, the accuracy of SVM-based forecast models was similar but generally required a longer amount of testing time.