Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170426
Xiahua Yang, P. Xue
Several discrete orthogonal transforms have been used to study the behaviors of transform-domain backpropagation (BP) algorithms. Two examples of computer simulation show that, on selecting the appropriate parameters and the suitable structures of a neural network, the performance of the transform-domain BP algorithm is somewhat better than that of the original time-domain BP algorithm, regardless of which discrete orthogonal transform is applied. Among the transforms that have been used, the behaviors of the discrete cosine transform (DCT) and an alternative version of it are believed to be the best.<>
{"title":"Behaviors of transform domain backpropagation (BP) algorithm","authors":"Xiahua Yang, P. Xue","doi":"10.1109/IJCNN.1991.170426","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170426","url":null,"abstract":"Several discrete orthogonal transforms have been used to study the behaviors of transform-domain backpropagation (BP) algorithms. Two examples of computer simulation show that, on selecting the appropriate parameters and the suitable structures of a neural network, the performance of the transform-domain BP algorithm is somewhat better than that of the original time-domain BP algorithm, regardless of which discrete orthogonal transform is applied. Among the transforms that have been used, the behaviors of the discrete cosine transform (DCT) and an alternative version of it are believed to be the best.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133721426","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170414
K. Imai, K. Gouhara, Y. Uchikawa
The authors present a novel pattern recognition architecture using three-layered backpropagation (BP) models. The proposed architecture consists mainly of the following two completely separate functions: extraction of a target pattern and recognition of the extracted pattern. It is possible that the proposed architecture detects where and what the target pattern is. In order to realize these functions, the following networks are introduced: filtering network, position network, size network, frame-working network, and categorizing networks. Results of handwritten-letter recognition experiments show that the proposed architecture has the ability to recognize a deformed target pattern in an original image with much noise, especially lumped noises.<>
{"title":"Pattern extraction and recognition for noisy images using the three-layered BP model","authors":"K. Imai, K. Gouhara, Y. Uchikawa","doi":"10.1109/IJCNN.1991.170414","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170414","url":null,"abstract":"The authors present a novel pattern recognition architecture using three-layered backpropagation (BP) models. The proposed architecture consists mainly of the following two completely separate functions: extraction of a target pattern and recognition of the extracted pattern. It is possible that the proposed architecture detects where and what the target pattern is. In order to realize these functions, the following networks are introduced: filtering network, position network, size network, frame-working network, and categorizing networks. Results of handwritten-letter recognition experiments show that the proposed architecture has the ability to recognize a deformed target pattern in an original image with much noise, especially lumped noises.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134040708","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170644
C.-M. Cho, H.-S. Don
A fast learning algorithm is proposed for training of multilayer feedforward neural networks, based on a combination of optimal linear Kalman filtering theory and error propagation. In this algorithm, all the information available from the start of the training process to the current training sample is exploited in the update procedure for the weight vector of each neuron in the network in an efficient parallel recursive method. This innovation is a massively parallel implementation and has better convergence properties than the conventional backpropagation learning technique. Its performance is illustrated on some examples, such as a XOR logical operation and a nonlinear mapping of two continuous signals.<>
{"title":"A parallel Kalman algorithm for fast learning of multilayer neural networks","authors":"C.-M. Cho, H.-S. Don","doi":"10.1109/IJCNN.1991.170644","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170644","url":null,"abstract":"A fast learning algorithm is proposed for training of multilayer feedforward neural networks, based on a combination of optimal linear Kalman filtering theory and error propagation. In this algorithm, all the information available from the start of the training process to the current training sample is exploited in the update procedure for the weight vector of each neuron in the network in an efficient parallel recursive method. This innovation is a massively parallel implementation and has better convergence properties than the conventional backpropagation learning technique. Its performance is illustrated on some examples, such as a XOR logical operation and a nonlinear mapping of two continuous signals.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131892497","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170507
S. Kia, G. Coghill
Presents an analog version of an artificial neural network, termed a differentiator, based on a variation of the competitive learning method. The network is trained in an unsupervised fashion, and it can be used for estimating the centroids of clusters of patterns. A dynamic competition is held among the competing neurons in adaptation to the input patterns with the aid of a novel type of neuron called control neuron. The output of the control neurons provides feedback reinforcement signals to modify the weight vectors during training. The training algorithm is different from conventional competitive learning methods in the sense that all the weight vectors are modified at each step of training. Computer simulation results are presented which demonstrate the behavior of the differentiator in estimating the class centroids. The results indicate the high power of dynamic competitive learning as well as the fast convergence rates of the weight vectors.<>
{"title":"Dynamic competitive learning for centroid estimation","authors":"S. Kia, G. Coghill","doi":"10.1109/IJCNN.1991.170507","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170507","url":null,"abstract":"Presents an analog version of an artificial neural network, termed a differentiator, based on a variation of the competitive learning method. The network is trained in an unsupervised fashion, and it can be used for estimating the centroids of clusters of patterns. A dynamic competition is held among the competing neurons in adaptation to the input patterns with the aid of a novel type of neuron called control neuron. The output of the control neurons provides feedback reinforcement signals to modify the weight vectors during training. The training algorithm is different from conventional competitive learning methods in the sense that all the weight vectors are modified at each step of training. Computer simulation results are presented which demonstrate the behavior of the differentiator in estimating the class centroids. The results indicate the high power of dynamic competitive learning as well as the fast convergence rates of the weight vectors.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134355715","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170712
Shulin Yang, Youan Ke, Zhong Wang
The application of the pyramidical multilayered neural net to speaker-independent recognition of isolated Chinese syllables was investigated. The feature extraction algorithm is described. Experiments involving 90 speakers from 25 provinces of China show that accuracies of 82.7% and 87.1% can be achieved, respectively, for ten isolated digits and seven typical syllables, and an over 75% cross-sex recognition rate can be obtained. The results indicate that this neural net technique can be applied to speaker-independent syllable recognition and that its performance is comparable to that of the hidden Markov model method.<>
{"title":"Speaker-independent syllable recognition by a pyramidical neural net","authors":"Shulin Yang, Youan Ke, Zhong Wang","doi":"10.1109/IJCNN.1991.170712","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170712","url":null,"abstract":"The application of the pyramidical multilayered neural net to speaker-independent recognition of isolated Chinese syllables was investigated. The feature extraction algorithm is described. Experiments involving 90 speakers from 25 provinces of China show that accuracies of 82.7% and 87.1% can be achieved, respectively, for ten isolated digits and seven typical syllables, and an over 75% cross-sex recognition rate can be obtained. The results indicate that this neural net technique can be applied to speaker-independent syllable recognition and that its performance is comparable to that of the hidden Markov model method.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130336016","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170486
R. Gemello, F. Mana
Describes a modification of the basic MLP (multilayer perceptron) model implemented to improve its capability to enforce closed decision regions. The authors' proposal is to use hyperspheres instead of hyperplanes on the first hidden layer, and in turn combine them through the next layers. After training, the decision regions will be naturally closed because they are built on simple computational elements which will fire only if the pattern will fall in the hypersphere receptive fields. The training is achieved by applying a modification of the basic backpropagation error without use of ad-hoc algorithms. A two-dimensional example is reported.<>
{"title":"An enhancement to MLP model to enforce closed decision regions","authors":"R. Gemello, F. Mana","doi":"10.1109/IJCNN.1991.170486","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170486","url":null,"abstract":"Describes a modification of the basic MLP (multilayer perceptron) model implemented to improve its capability to enforce closed decision regions. The authors' proposal is to use hyperspheres instead of hyperplanes on the first hidden layer, and in turn combine them through the next layers. After training, the decision regions will be naturally closed because they are built on simple computational elements which will fire only if the pattern will fall in the hypersphere receptive fields. The training is achieved by applying a modification of the basic backpropagation error without use of ad-hoc algorithms. A two-dimensional example is reported.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"8 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130337609","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170597
M. V. Van Hulle, T. Tollenaere, G. Orban
Explores two sources of inaccuracies originating from the use of local line detectors for inferring curve and boundary traces: (1) due to the position uncertainty of the local line detectors, ends of thin lines are not easily detected, even if cross-orientation inhibition is applied; and (2) due to the limited ability of the local line detectors to assess more global trace information gaps appear in the curve and boundary extracted. It is shown how a single EDANN (entropy drive artificial neural networks) module processing the orientation of illumination contrast compensates for these inaccuracies by performing a two-stage detection process, a competitive and a cooperative one. In the competitive stage, a vector field of tangents to curves and boundaries is extracted by using elongated receptive fields. In the cooperative stage, line-ends are extracted and boundary gaps are bridged by broadening the neuron's orientation tuning curves.<>
{"title":"Line-end detection and boundary gap completion in an EDANN module for orientation","authors":"M. V. Van Hulle, T. Tollenaere, G. Orban","doi":"10.1109/IJCNN.1991.170597","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170597","url":null,"abstract":"Explores two sources of inaccuracies originating from the use of local line detectors for inferring curve and boundary traces: (1) due to the position uncertainty of the local line detectors, ends of thin lines are not easily detected, even if cross-orientation inhibition is applied; and (2) due to the limited ability of the local line detectors to assess more global trace information gaps appear in the curve and boundary extracted. It is shown how a single EDANN (entropy drive artificial neural networks) module processing the orientation of illumination contrast compensates for these inaccuracies by performing a two-stage detection process, a competitive and a cooperative one. In the competitive stage, a vector field of tangents to curves and boundaries is extracted by using elongated receptive fields. In the cooperative stage, line-ends are extracted and boundary gaps are bridged by broadening the neuron's orientation tuning curves.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124289002","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170513
B. Xu, L. Zheng
It is pointed out that the planar topology of the current backpropagation neural network (BPNN) sets limits to the solution of the slow convergence rate problem, local minima, and other problems associated with BPNN. The parallel probabilistic neural network (PPNN) using a novel neural network topology, stereotopology, is proposed to overcome these problems. The learning ability and the generation ability of BPNN and PPNN are compared for several problems. Simulation results show that PPNN was capable of learning various kinds of problems much faster than BPNN, and also generalized better than BPNN. It is shown that the faster, universal learnability of PPNN was due to the parallel characteristic of PPNN's stereotopology, and the better generalization ability came from the probabilistic characteristic of PPNN's memory retrieval rule.<>
{"title":"PPNN: a faster learning and better generalizing neural net","authors":"B. Xu, L. Zheng","doi":"10.1109/IJCNN.1991.170513","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170513","url":null,"abstract":"It is pointed out that the planar topology of the current backpropagation neural network (BPNN) sets limits to the solution of the slow convergence rate problem, local minima, and other problems associated with BPNN. The parallel probabilistic neural network (PPNN) using a novel neural network topology, stereotopology, is proposed to overcome these problems. The learning ability and the generation ability of BPNN and PPNN are compared for several problems. Simulation results show that PPNN was capable of learning various kinds of problems much faster than BPNN, and also generalized better than BPNN. It is shown that the faster, universal learnability of PPNN was due to the parallel characteristic of PPNN's stereotopology, and the better generalization ability came from the probabilistic characteristic of PPNN's memory retrieval rule.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124836946","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170649
D. Mansor, D. Suter
The resistive grid approach has been adopted by the Harris coupled depth-slope analog network and generalized for regularization involving arbitrary degrees of smoothness. The authors consider implementations of arbitrary order regularization networks which do not require resistive grids. The approach followed is to generalize the original formulation of J.G. Harris (1987) and then to follow alternative paths to analog circuit realization allowed by the generalization.<>
{"title":"Implementation of visual reconstruction networks-Alternatives to resistive networks","authors":"D. Mansor, D. Suter","doi":"10.1109/IJCNN.1991.170649","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170649","url":null,"abstract":"The resistive grid approach has been adopted by the Harris coupled depth-slope analog network and generalized for regularization involving arbitrary degrees of smoothness. The authors consider implementations of arbitrary order regularization networks which do not require resistive grids. The approach followed is to generalize the original formulation of J.G. Harris (1987) and then to follow alternative paths to analog circuit realization allowed by the generalization.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124889787","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}
Pub Date : 1991-11-18DOI: 10.1109/IJCNN.1991.170567
P.T.H. Chan, M. Palaniswami, D. Everitt
Conventional dynamic channel assignment schemes are both time-consuming and algorithmically complex. An alternative approach using a multilayered feedforward neural network model is examined. The results of the neural network approach are compared with those of a maximum packing strategy technique. The comparison shows that the neural networks approach is well-suited to the dynamic channel allocation problem.<>
{"title":"Dynamic channel assignment for cellular mobile radio system using feedforward neural networks","authors":"P.T.H. Chan, M. Palaniswami, D. Everitt","doi":"10.1109/IJCNN.1991.170567","DOIUrl":"https://doi.org/10.1109/IJCNN.1991.170567","url":null,"abstract":"Conventional dynamic channel assignment schemes are both time-consuming and algorithmically complex. An alternative approach using a multilayered feedforward neural network model is examined. The results of the neural network approach are compared with those of a maximum packing strategy technique. The comparison shows that the neural networks approach is well-suited to the dynamic channel allocation problem.<<ETX>>","PeriodicalId":211135,"journal":{"name":"[Proceedings] 1991 IEEE International Joint Conference on Neural Networks","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132046014","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：