{"title":"Optimum frequencies selection for radar target classification by neural network","authors":"Jungang Xu, Zhong Wang, Youan Ke","doi":"10.1109/IJCNN.1991.170566","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170566","url":null,"abstract":"A simple method for selecting the optimum frequencies for radar target classification using a backpropagation neural network (BNN) is presented. Results indicate that the BNN can be used not only for identifying radar targets in the frequency domain, but also for determining the optimum frequencies as an additive result in the learning process of the BNN. This method is based on the sensitivity analysis of the input nodes of the BNN. The frequencies corresponding to the input nodes which have maximum sensitivities are selected as the optimum frequencies. This method was verified on five simple radar targets.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124154891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Microcanonical mean field annealing: a new algorithm for increasing the convergence speed of mean field annealing","authors":"N. Lee, A. Louri","doi":"10.1109/IJCNN.1991.170521","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170521","url":null,"abstract":"The authors consider the convergence speed of mean field annealing (MFA). They combine MFA with the microcanonical simulation (MCS) method and propose an algorithm called microcanonical mean field annealing (MCMFA). In the proposed algorithm, cooling speed is controlled by current temperature so that computation in the MFA can be reduced without degradation of performance. In addition, the solution quality of MCMFA is not affected by the initial temperature. The properties of MCMFA are analyzed with a simple example and simulated with Hopfield neural networks. In order to compare MCMFA with MFA, both algorithms are applied to graph bipartitioning problems. Simulation results show that MCMFA produces a better solution than MFA.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124192317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Inverse modeling of dynamical system-network architecture with identification network and adaptation network","authors":"T. Kimoto, Y. Yaginuma, S. Nagata, K. Asakawa","doi":"10.1109/IJCNN.1991.170460","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170460","url":null,"abstract":"The authors describe a neural network architecture enabling inverse modeling of a nonlinear dynamical system. It consists of two neural networks, a system identification network and an adaptation network. The effectiveness of the proposed network architecture is examined by applying it to a digital mobile communication adaptive equalizer. In digital mobile communication, the problem of multipath fading caused by vehicular movement becomes a nonlinear dynamical system. The proposed network architecture is able to obtain an inverse model of such transmission channels and attain equalization of signal distortions. The performance of the proposed adaptive equalizer was evaluated by computer simulation. The bit error rate was found to decrease by one-third compared to that without an equalizer.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124535182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A solid-state electronic linear adaptive neuron with electrically alterable synapses","authors":"C.-Y.M. Chen, M. White, M. French","doi":"10.1109/IJCNN.1991.170616","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170616","url":null,"abstract":"The authors address the hardware implementation of a semiconductor device which emulates the biological synaptic interconnection for the hardware realization of neural network systems. Specifically, they describe work on the electrically reprogrammable (alterable) SONOS (silicon blocking oxide nitride tunneling oxide silicon) nonvolatile synapse and a simple electronic neuron which incorporates these alterable synapses. The electronic synaptic interconnection strength, or the weight value, can be electrically altered at CMOS voltage levels. The authors have incorporated these modifiable synaptic weights into a solid-state electronic linear adaptive neuron with a Widrow-Hoff's delta learning rule as the updating algorithm to examine the electrical performance of these programmable synapses. The experimental results and the desirable features of these electronic synapses are discussed.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114757611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Experiments with ordering attributes for efficient connectionist system development","authors":"H. Ferrá, A. Kowalczyk, A. Jennings","doi":"10.1109/IJCNN.1991.170317","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170317","url":null,"abstract":"The authors introduce an algorithm for selection and ordering of input attributes based on a generalization to a fuzzy case of the notion of conditional entropy. The algorithm is relatively computationally inexpensive and efficient, as was demonstrated in a number of experiments that are reported. The experimental results support the observation that preselection and ordering of a small number of effective input features constitute an important factor in the development of efficient neural network classifiers.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116887032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A car detection system using the neocognitron","authors":"S. Yamaguchi, H. Itakura","doi":"10.1109/IJCNN.1991.170561","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170561","url":null,"abstract":"A car image detection system using the neocognitron is described. The system can recognize car images successfully without regard to influences of the differences of kinds of cars and shifts in position. The number of cell planes can be reduced by actively introducing features of patterns to be recognized by the neocognitron. The neocognitron uses vertical and horizontal lines and combinations as training patterns. The increase of the number of cell planes can thus be held down. Although car images are not directly used in the training process except in the output layer, the system can detect cars skilfully. Thus, using appropriate features of input patterns, the neocognitron obtains sufficient recognition capability.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116190144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A general purpose neurocomputer","authors":"F. B. Verona, P. De Pinto, F. Lauria, M. Sette","doi":"10.1109/IJCNN.1991.170428","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170428","url":null,"abstract":"Presents a neural network, composed of linear units with threshold, as the CPU of a stored program MIMD architecture. The Caianiello formalism, is introduced as an aid to implement the arithmetic and control algorithms, needed for the smooth running of this general-purpose system. That is, in the neural net both the arithmetic and logic algorithms and the operating system have been implemented. The latter is diffuse as it has been co-implemented with the single arithmetic operations. It controls each operation I/O, the input, output and intermediate data buffers, the clerical work associated to the beginning and the end of a task execution, etc. The neural net control is data-driven, i.e. the incoming data are the very signals telling the net to execute its task. As the net is data-driven, the system supports an efficient run time resource allocation algorithm. That is, at run time the incoming instructions chase the available resources and the waiting time, spent by the data in presence of idle resources, is minimized. At the same time, the system pipelines, automatically, nested loops, of arbitrary depth, and accepts unlimited recursive calls of routines.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116385587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Figueroa-Nazuno, G. Perez-Elizalde, E. Vargas-Medina, M. G. Raggi-Gonzalez
{"title":"Information representation analysis in a neural network","authors":"J. Figueroa-Nazuno, G. Perez-Elizalde, E. Vargas-Medina, M. G. Raggi-Gonzalez","doi":"10.1109/IJCNN.1991.170721","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170721","url":null,"abstract":"The authors study the mathematical behavior of the hidden layer of a generalized delta rule type neural network (GDR) by analyzing the weights and thresholds in the network, when it learned and didn't learn, in a typical situation in neurocomputation. The GDR was used in a C language program. There are three representation hypotheses: (a) the local, which states that information encoding takes place in local parts of the network; (b) the generalized, which states that information is located in extended areas in the network; and (c) the global, which states that total behavior represents the information in the networks. Several intensive computations were carried out to analyze the neural network internal behavior in situations where it did and didn't learn. The information shows clearly that representation as a global behavior in the hidden layer is responsible for learning, and not local behavior situations.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123231588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A multilayered neural net controller for servo systems","authors":"E. Khan, T. Ogunfunmi","doi":"10.1109/IJCNN.1991.170633","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170633","url":null,"abstract":"The authors investigate the possibility of adding a multilayered feedforward neural network controller to an existing servomotor controller to make it an intelligent adaptive controller. The use of the existing controller guarantees coarse learning and thus provides better generalization and correction capabilities. Several learning algorithms are proposed to properly correct the motor inputs under various system nonlinearities, parameter variations over time, and uncertainties. Simulations show very encouraging results. The performance of the proposed controller is compared with that of a proportional-integral-derivative (PID) controller and a model reference adaptive (MRAC) controller.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123514931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A face graph method using a fuzzy neural network for expressing conditions of complex systems","authors":"T. Hashiyama, T. Furuhashi, Y. Uchikawa, H. Kato","doi":"10.1109/IJCNN.1991.170356","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170356","url":null,"abstract":"The face graph method with such varying elements as dyes, eyebrows, mouth, etc. is used for expressing multidimensional data. Since human beings are very sensitive to human faces, one can easily evaluate the multidimensional data expressed by the face graph. The authors present a novel approach of the face graph method using a fuzzy neural network for expressing conditions of complex systems. Experiments are carried out to make the face graphs correspond to the conditions of an electric circuit.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123647799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}