A gradual neural network approach for FPGA segmented channelrouting problems

A novel neural network approach called gradual neural network (GNN) is presented for segmented channel routing in field programmable gate arrays (FPGA's). FPGA's contain predefined segmented channels for net routing, where adjacent segments in a track can be interconnected through programmable switches for longer segments. The goal of the FPGA segmented channel routing problem, known to be NP-complete, is to find a conflict-free net routing with the minimum routing cost. The GNN for the N-net-M-track problem consists of a neural network of NxM binary neurons and a gradual expansion scheme. The neural network satisfies the constraints of the problem, while the gradual expansion scheme seeks the cost minimization by gradually increasing activated neurons. The energy function and the motion equation are newly defined with heuristic methods. The performance is verified through solving 30 instances, where GNN finds better solutions than existing algorithms within a constant number of iteration steps.     

A gradual neural-network algorithm for jointly time-slot/code assignment problems in packet radio networks

A gradual neural network (GNN) algorithm is presented for the jointly time-slot/code assignment problem (JTCAP) in a packet radio network in this paper. The goal of this newly defined problem is to find a simultaneous assignment of a time-slot and a code to each communication link, whereas time-slots and codes have been independently assigned in existing algorithms. A time/code division multiple access protocol is adopted for conflict-free communications, where packets are transmitted in repetition of fixed-length time-slots with specific codes. GNN seeks the time-slot/code assignment with the minimum number of time-slots subject to two constraints: (1) the number of codes must not exceed its upper limit and (2) any couple of links within conflict distance must not be assigned to the same time-slot/code pair. The restricted problem for only one code is known to be NP-complete. The performance of GNN is verified through solving 3000 instances with 100-500 nodes and 100-1000 links. The comparison with the lower bound and a greedy algorithm shows the superiority of GNN in terms of the solution quality with the comparable computation time.     

A hybrid hopfield network-simulated annealing approach for frequency assignment in satellite communications systems.

A hybrid Hopfield network-simulated annealing algorithm (HopSA) is presented for the frequency assignment problem (FAP) in satellite communications. The goal of this NP-complete problem is minimizing the cochannel interference between satellite communication systems by rearranging the frequency assignment, for the systems can accommodate the increasing demands. The HopSA algorithm consists of a fast digital Hopfield neural network which manages the problem constraints hybridized with a simulated annealing which improves the quality of the solutions obtained. We analyze the problem and its formulation, describing and discussing the HopSA algorithm and solving a set of benchmark problems. The results obtained are compared with other existing approaches in order to show the performance of the HopSA approach.     

A Hybrid Neural-Genetic Algorithm for the Frequency Assignment Problem in Satellite Communications

A hybrid Neural-Genetic algorithm (NG) is presented for the frequency assignment problem in satellite communications (FAPSC). The goal of this problem is minimizing the cochannel interference between satellite communication systems by rearranging the frequency assignments. Previous approaches to FAPSC show lack of scalability, which leads to poor results when the size of the problem grows. The NG algorithm consists of a Hopfield neural network which manages the problem constraints hybridized with a genetic algorithm for improving the solutions obtained. This separate management of constraints and optimization of objective function gives the NG algorithm the properties of scalability required.We analyze the FAPSC and its formulation, describe and discuss the NG algorithm and solve a set of benchmark problems. The results obtained are compared with other existing approaches in order to show that the NG algorithm is more scalable and performs better than previous algorithms in the FAPSC.This work was supported in part by CICYT under grant TIC 1999-0216     

A hybrid approach based on stochastic competitive Hopfield neural network and efficient genetic algorithm for frequency assignment problem

This paper presents a hybrid efficient genetic algorithm (EGA) for the stochastic competitive Hopfield (SCH) neural network, which is named SCH–EGA. This approach aims to tackle the frequency assignment problem (FAP). The objective of the FAP in satellite communication system is to minimize the co-channel interference between satellite communication systems by rearranging the frequency assignment so that they can accommodate increasing demands. Our hybrid algorithm involves a stochastic competitive Hopfield neural network (SCHNN) which manages the problem constraints, when a genetic algorithm searches for high quality solutions with the minimum possible cost. Our hybrid algorithm, reflecting a special type of algorithm hybrid thought, owns good adaptability which cannot only deal with the FAP, but also cope with other problems including the clustering, classification, and the maximum clique problem, etc. In this paper, we first propose five optimal strategies to build an efficient genetic algorithm. Then we explore three hybridizations between SCHNN and EGA to discover the best hybrid algorithm. We believe that the comparison can also be helpful for hybridizations between neural networks and other evolutionary algorithms such as the particle swarm optimization algorithm, the artificial bee colony algorithm, etc. In the experiments, our hybrid algorithm obtains better or comparable performance than other algorithms on 5 benchmark problems and 12 large problems randomly generated. Finally, we show that our hybrid algorithm can obtain good results with a small size population.     

A binary Hopfield neural-network approach for satellite broadcastscheduling problems

This paper presents a binary Hopfield neural network approach for finding a broadcasting schedule in a low-altitude satellite system. Our neural network is composed of simple binary neurons on the synchronous parallel computation, which is greatly suitable for implementation on a digital machine. With the help of heuristic methods, the neural network of a maximum of 200000 neurons can always find near-optimum solutions on a conventional workstation in our simulations.     

面向异构通信卫星的地球站组网规划方法

经过多年的建设发展,卫星通信已经形成了多系列卫星并存、相互支撑、相互补充的通信系统.然而,由于各卫星系统建设时间跨度大,通信技术手段存在差异,如何高效利用异构的卫星通信资源成为了一个实际难题.为此,文中首次根据卫星与地球站的可互通条件构建了系统模型,并将其归结为线性约束下离散变量的非线性优化问题,优化目标是异构卫星波束...     

Multi-start stochastic competitive Hopfield neural network for frequency assignment problem in satellite communications

The objective of the frequency assignment problem (FAP) is to minimize cochannel interference between two satellite systems by rearranging frequency assignment. In this paper, we first propose a competitive Hopfield neural network (CHNN) for FAP. Then we propose a stochastic CHNN (SCHNN) for the problem by introducing stochastic dynamics into the CHNN to help the network escape from local minima. In order to further improve the performance of the SCHNN, a multi-start strategy or re-start mechanism is introduced into the SCHNN. The multi-start strategy or re-start mechanism super-imposed on the SCHNN is characterized by alternating phases of cooling and reheating the stochastic dynamics, thus provides a means to achieve an effective dynamic or oscillating balance between intensification and diversification during the search. Furthermore, dynamic weighting coefficient setting strategy is adopted in the energy function to satisfy the constraints and improve the objective of the problem simultaneously. The proposed multi-start SCHNN (MS-SCHNN) is tested on a set of benchmark problems and a large number of randomly generated instances. Simulation results show that the MS-SCHNN is better than several typical neural network algorithms such as GNN, TCNN, NCNN and NCNN-VT, and metaheuristic algorithm such as hybrid SA.     

不确定分数阶多涡卷混沌系统自适应重复学习同步控制

研究了不确定分数阶多涡卷混沌系统的自适应重复学习同步控制问题.通过利用滞环函数,设计了一类参数可调的分数阶多涡卷混沌系统.针对这类分数阶多涡卷混沌系统,在考虑非参数化不确定性、周期时变参数化不确定性、常参数化不确定性和外部扰动情况下,提出了一种重复学习同步控制方案.利用自适应神经网络技术补偿了系统中的函数型不确定性,通过自适应重复学习控制技术处理了周期时变参数化不确定性,并利用自适应鲁棒学习项处理了神经网络逼近误差和干扰的影响,实现了主系统和从系统的完全同步.综合利用分数阶频率分布模型和类Lyapunov复合能量函数方法证明了同步误差的学习收敛性.数值仿真验证了所提方法的有效性.     

大规模图神经网络系统综述

图神经网络(GNN)是一类基于深度学习的处理图域信息的方法,它通过将图广播操作和深度学习算法结合,可以让图的结构信息和顶点属性信息都参与到学习中,在顶点分类、图分类、链接预测等应用中表现出良好的效果和可解释性,已成为一种广泛应用的图分析方法.然而现有主流的深度学习框架(如TensorFlow、PyTorch等)没有为图...     

A Chaotic Annealing Neural Network with Gain Sharpening and Its Application to the 0/1 Knapsack Problem

In this article we present a modified transiently chaotic neural network model and then use it to solve the 0/1 knapsack problem. During the chaotic searching the gain of the neurons is gradually sharpened, this strategy can accelerate the convergence of the network to a binary state and keep the satisfaction of the constraints. The simulation demonstrates that the approach is efficient both in approximating the global solution and the number of iterations.     

A gradual noisy chaotic neural network for solving the broadcast scheduling problem in packet radio networks

In this paper, we propose a gradual noisy chaotic neural network (G-NCNN) to solve the NP-complete broadcast scheduling problem (BSP) in packet radio networks. The objective of the BSP is to design an optimal time-division multiple-access (TDMA) frame structure with minimal TDMA frame length and maximal channel utilization. A two-phase optimization is adopted to achieve the two objectives with two different energy functions, so that the G-NCNN not only finds the minimum TDMA frame length but also maximizes the total node transmissions. In the first phase, we propose a G-NCNN which combines the noisy chaotic neural network (NCNN) and the gradual expansion scheme to find a minimal TDMA frame length. In the second phase, the NCNN is used to find maximal node transmissions in the TDMA frame obtained in the first phase. The performance is evaluated through several benchmark examples and 600 randomly generated instances. The results show that the G-NCNN outperforms previous approaches, such as mean field annealing, a hybrid Hopfield network-genetic algorithm, the sequential vertex coloring algorithm, and the gradual neural network.     

图神经网络推荐研究进展

图神经网络(graph neural network, GNN)具有从图的领域对数据进行特征提取和表示的优势,近年来成为人工智能研究的热点,图神经网络推荐也是推荐系统研究的一个新方向。本文对GNN模型进行深入研究的基础上,分析了GNN推荐过程,并从无向单元图推荐、无向二元图推荐、无向多元图推荐3个方面详细讨论了现有GNN推荐研究取得的主要进展及不足,阐明了现有GNN推荐研究中存在的主要难点,最后提出了GNN上下文推荐、GNN跨领域推荐、GNN群组推荐、GNN推荐的可解释性等未来GNN推荐的研究方向。     

Fourier-Neural-Network-Based Learning Control for a Class of Nonlinear Systems With Flexible Components

This paper considers an output feedback learning control for a class of uncertain nonlinear systems with flexible components. The distinct time delay caused by system flexibility leads to the phase lag phenomenon and low system bandwidth. Therefore, the tracking problem of such systems is very difficult and challenging. To improve the tracking performance of such systems, an iterative learning control scheme using the Fourier neural network (FNN) is presented in this paper. This scheme uses only local output information for feedback. FNN employs orthogonal complex Fourier exponentials as its activation functions and the physical meaning of its hidden-layer neurons is clear. The FNN-based learning controller introduced here relies on the frequency-domain method, which converts the tracking problem in the time domain into a number of regulation problems in the frequency domain. A novel phase compensation method is introduced to deal with the phase lag phenomenon, so that the bandwidth of the closed-loop system is increased. Experiments on a belt-driven positioning table are conducted to show the effectiveness of the proposed controller.     

A novel fused neural network controller for lateral control of autonomous vehicles

We present a novel fused feed-forward neural network controller inspired by the notion of task decomposition principle. The controller is structurally simple and can be applied to a class of control systems that their control requires manipulation of two input variables. The benchmark problem of inverted pendulum is such example that its control requires availability of the angle as well as the displacement. We demonstrate that the lateral control of autonomous vehicles belongs to this class of systems and successfully apply the proposed controller to this problem. The parameters of the controller are encoded into real value chromosomes for genetic algorithm (GA) optimization. The neural network controller contains three neurons and six connection weights implying a small search space implying faster optimization time due to few controller parameters. The controller is also tested on two benchmark control problems of inverted pendulum and the ball-and-beam system. In particular, we apply the controller to lateral control of a prototype semi-autonomous vehicle. Simulation results suggest a good performance for all the tested systems. To demonstrate the robustness of the controller, we conduct Monte-Carlo evaluations when the system is subjected to random parameter uncertainty. Finally experimental studies on the lateral control of a prototype autonomous vehicle with different speed of operation are included. The simulation and experimental studies suggest the feasibility of this controller for numerous applications.     

New Results on Convergence of CNNs with Neutral Type Proportional Delays and D Operator

It was shown that the multiplication of the left hand side of the classical Zhang neural network design rule by an appropriate positive definite matrix generates a new neural design with improved convergence rate. Our intention is to apply similar principle on the standard gradient neural network (GNN) model. To that goal, we discover that some of proposed models can be considered as the multiplication of the right hand side of the GNN model by a symmetric positive-semidefinite matrix. As a final result, we propose appropriate general pattern to define various improvements of the standard GNN design for online real-time matrix inversion in time invariant case. The leading idea in generating improved models is initiated after a combination of two GNN patterns. Improved GNN (IGNN) design shows global exponential convergence with an improved convergence rate with respect to the convergence rate of the original GNN pattern. The acceleration in the convergence rate is defined by the smallest eigenvalue of appropriate positive semidefinite matrices. IGNN models are not only generalizations of original GNN models but they comprise so far defined improvements of the standard GNN design.     

基于信任的低地球轨道卫星网络路由安全机制

将基于信任的路由安全机制引入卫星网络路由,提出一种信任评估模型,用信任度约束选路过程,以路由负载均衡为优化目标,对现有路由协议进行安全性改进,在此基础上,设计适用于卫星网络的按需安全路由协议。分析结果表明,该协议能够防范多种常见的内部攻击。     

基于神经网络的周期扰动非线性系统自适应渐近跟踪控制

针对一类具有周期扰动和输入时滞的不确定非线性系统,提出一种基于神经网络的自适应动态面控制方案.将径向基函数神经网络和傅里叶级数展开结合,构造一种混合函数逼近器来逼近系统中未知的周期扰动函数.通过引入一个积分项解决输入时滞问题,同时采用带有非线性滤波器的动态面控制方法,避免自适应反推控制方法中普遍存在的复杂性爆炸问题.所...     

An Annealed Chaotic Competitive Learning Network with Nonlinear Self-feedback and Its Application in Edge Detection

An unsupervised parallel approach called Annealed Chaotic Competitive Learning Network (ACCLN) for the optimization problem is proposed in this paper. The goal is to modify an unsupervised scheme based on the competitive neural network using the chaotic technique governed by an annealing strategy so that on-line learning and parallel implementation to find near-global solution for image edge detection is feasible. In the ACCLN, the edge detection is conceptually considered as a clustering problem. Here, it is a kind of competitive learning network model imposed by a 2-dimensional input layer and an output layer working toward minimizing an objective function defined as the contextual information. The interconnection strength, composed by an internal state and a transient state with a non-linear self-feedback manner, is connected between neurons in input and output layers. To harness the chaotic dynamic and convergence process, an annealing strategy is also embedded into the ACCLN. In addition to retain the characteristics of the conventional neural units, the ACCLN displays a rich range of behavior reminiscent of that observed in neurons. Unlike the conventional neural network, the ACCLN has rich range and flexible dynamics, so that it can be expected to have higher ability of searching for globally optimal or near-optimum results.