{"title":"Reconstruction of blood vessel networks from a few perspective projections","authors":"Peter Hall, Peter M. Andreae, M. Ngan","doi":"10.1109/ANNES.1995.499510","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499510","url":null,"abstract":"We are investigating systems that accept a few two dimensional images that are perspective projections of blood vessels to reconstruct a three dimensional model of those vessels. This task is impossible unless a priori information is used; how this information is represented is widely regarded as a key issue. We describe the form that our system uses and explain why it is an improvement on previous representations. In particular, we show that the representation is extensible in that new information can be added to it at any time, and that the representation is task independent, in the sense that it can be used in many ways. We demonstrate its application to the problem of reconstruction and discuss how the representation can be \"learned from observation\".","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123789870","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":"Convergent unlearning algorithm for the Hopfield neural network","authors":"A. Plakhov, S. A. Semenov, Irina B. Shuvalova","doi":"10.1109/ANNES.1995.499432","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499432","url":null,"abstract":"We investigate asymptotic behaviour of synaptic matrix iterated according to the unlearning algorithm (A. Yu et al., 1994). The algorithm has been proven to converge to the projector (pseudo inverse) rule matrix if the unlearning strength parameter /spl epsi/>0 does not exceed some critical value. Asymptotic behaviour of normalized synaptic matrix J/spl tilde/ is considered, relating it to the corresponding spectrum dynamics. It is found that the algorithm converges for arbitrary value of /spl epsi/, and there are only three possibilities for limiting behaviour of J/spl tilde/. The first one is successful unlearning which implies the convergence to the projection matrix onto the linear subspace /spl Lscr/ spanned by maximal subset of linearly independent patterns. At sufficiently large values of /spl epsi/ the typical result of iterations will be failed unlearning, with J/spl tilde/ converging to the minus projector on random unity vector /spl xi//spl isin//spl Lscr/. We show that failed unlearning results in total memory breakdown. There is also an \"intermediate\" case when J/spl tilde/ converges to the projection matrix on some subspace of /spl Lscr/. Probability for different asymptotics to appear depending upon unlearning strength is studied for the case of unbiased random patterns. Retrieval properties of the system equipped with limiting synaptic matrix are also discussed.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114561645","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":"An area efficient implementation of a cellular neural network","authors":"K. K. Lai, P. Leong","doi":"10.1109/ANNES.1995.499437","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499437","url":null,"abstract":"A time multiplexing scheme for implementing cellular neural networks (CNN) is described. This scheme makes it possible to realise much higher density implementations of CNNs in VLSI circuits. A circuit implementation of this technique is presented along with simulation results.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115783820","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}
A. Bulsara, M. Inchiosa, J. Lindner, B. Meadows, W. Ditto
{"title":"Noise-induced synchronized switching in coupled bistable systems","authors":"A. Bulsara, M. Inchiosa, J. Lindner, B. Meadows, W. Ditto","doi":"10.1109/ANNES.1995.499428","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499428","url":null,"abstract":"We consider a network of bistable dynamic elements with local, linear coupling, subject to noise and a time periodic signal. The response (quantified by an output signal to noise ratio, SNR) of a single element can be substantially enhanced when it is coupled into an array of like elements. In fact we show that noise and coupling cooperate to organize spatio temporal order across the array, corresponding to an increase in the output SNR of the reference element. The results shed new light on the potentially beneficial role of background noise in nonlinear dynamic devices and networks of neuron like elements.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130224679","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 proposal of emotional memory model","authors":"Kaori Yoshida, T. Yanaru","doi":"10.1109/ANNES.1995.499441","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499441","url":null,"abstract":"The paper introduces a basic concept of the emotional memory model. The proposed model is realized by two basic methods; (i) one is to introduce a matrix into the model, which is called a frame, as a set of arbitrary attributes extracting the basic features of emotional words, (ii) the emotional words are represented by any values considering how well fit the items of the frame are. The model discussed can be considered as a kind of emotional processing system, which may be developed as a human cognitive process model.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134107807","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":"Squad-based expert modules for closing diphthong recognition","authors":"J. Kirkland","doi":"10.1109/ANNES.1995.499494","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499494","url":null,"abstract":"The paper presents a new method of forming expert modules for modular time delay neural networks (modular TDNNs) using ensembles of similarly trained TDNNs referred to as squads. Squad base expert modules for closing diphthong recognition are compared with traditional expert modules comprising individual TDNNs and are found to afford significantly better false positive error performances, while recognition performances are comparable or better. Traditional and squad based expert modules formed from three different TDNN variants are compared. One of these variants, sequence token TDNN, embodies a novel method of using traditional TDNNs for closing diphthong recognition and is found to outperform the other variants when squad based expert modules are used.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131530728","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":"GA to optimize approximate solutions of fuzzy relational equations for fuzzy systems or controllers","authors":"M. Negoita, M. Giuclea","doi":"10.1109/ANNES.1995.499455","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499455","url":null,"abstract":"A GA (genetic algorithm) method for discrete time fuzzy model identification is proposed. The approach consists of three levels of optimization in order to minimize a quadratic performance index. Two numerical examples prove the applicability of this simultaneous optimization of the mentioned levels by GA.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133575168","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":"Climatic control of a storage chamber using fuzzy logic","authors":"P. Lim, N. R. Spooner, Bruce Gatland","doi":"10.1109/ANNES.1995.499459","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499459","url":null,"abstract":"Fuzzy logic has emerged as a superior control method for processes that are mathematically difficult to model. The paper investigates the potential of fuzzy logic for the control of a MIMO process with interactive process states. A fuzzy logic controller was designed and implemented for an industrial storage chamber where both temperature and humidity conditions are maintained during operation. Results from experiments and a comparison with PID control demonstrate the reliability and robustness of the controller under normal operating conditions and in the presence of disturbances.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131884760","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":"Neural network approaches to cognitive mapping","authors":"M. Jefferies, W. Yeap","doi":"10.1109/ANNES.1995.499443","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499443","url":null,"abstract":"There are many different approaches to cognitive mapping, arising mostly from the different philosophical backgrounds of the researchers involved. Our own research into the problem of how best to build a representation for one's experience of one's spatial environment is motivated by the need to understand how the human mind works. Neural network approaches to cognitive mapping are as varied as their non-neural network counterparts and range from models which use the network to model the physiology of the brain to models which are merely an abstraction of some aspect of cognitive mapping behaviour. We review four neural network approaches to cognitive mapping with the view to determining what insights they can bring to the cognitive mapping process.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114708635","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":"Hybrid systems for medical data analysis and decision making-a case study on varicose vein disorders","authors":"M. Bailey, C. Solomon, N. Kasabov, S. Greig","doi":"10.1109/ANNES.1995.499486","DOIUrl":"https://doi.org/10.1109/ANNES.1995.499486","url":null,"abstract":"This paper examines the applicability of intelligent information processing techniques for the analysis of vascular laboratory data associated with varicose vein disorders. In the first section a brief description of varicose disease is provided. Next, the notion of applying different types of neural network to learning the dynamics of the disease is examined in two experiments. Subsequent to these, a new approach to visualising the output of a Kohonen network is presented. A brief discussion then follows on an architecture for combining these networks into an intelligent hybrid decision making system. Finally, directions for future research are discussed.","PeriodicalId":123427,"journal":{"name":"Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123454712","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}