{"title":"“what-where”代码上的自组织映射,走向完全无监督分类。","authors":"Luis Sa-Couto, Andreas Wichert","doi":"10.1007/s00422-023-00963-y","DOIUrl":null,"url":null,"abstract":"<p><p>Interest in unsupervised learning architectures has been rising. Besides being biologically unnatural, it is costly to depend on large labeled data sets to get a well-performing classification system. Therefore, both the deep learning community and the more biologically-inspired models community have focused on proposing unsupervised techniques that can produce adequate hidden representations which can then be fed to a simpler supervised classifier. Despite great success with this approach, an ultimate dependence on a supervised model remains, which forces the number of classes to be known beforehand, and makes the system depend on labels to extract concepts. To overcome this limitation, recent work has been proposed that shows how a self-organizing map (SOM) can be used as a completely unsupervised classifier. However, to achieve success it required deep learning techniques to generate high quality embeddings. The purpose of this work is to show that we can use our previously proposed What-Where encoder in tandem with the SOM to get an end-to-end unsupervised system that is Hebbian. Such system, requires no labels to train nor does it require knowledge of which classes exist beforehand. It can be trained online and adapt to new classes that may emerge. As in the original work, we use the MNIST data set to run an experimental analysis and verify that the system achieves similar accuracies to the best ones reported thus far. Furthermore, we extend the analysis to the more difficult Fashion-MNIST problem and conclude that the system still performs.</p>","PeriodicalId":55374,"journal":{"name":"Biological Cybernetics","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10258173/pdf/","citationCount":"0","resultStr":"{\"title\":\"Self-organizing maps on \\\"what-where\\\" codes towards fully unsupervised classification.\",\"authors\":\"Luis Sa-Couto, Andreas Wichert\",\"doi\":\"10.1007/s00422-023-00963-y\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Interest in unsupervised learning architectures has been rising. Besides being biologically unnatural, it is costly to depend on large labeled data sets to get a well-performing classification system. Therefore, both the deep learning community and the more biologically-inspired models community have focused on proposing unsupervised techniques that can produce adequate hidden representations which can then be fed to a simpler supervised classifier. Despite great success with this approach, an ultimate dependence on a supervised model remains, which forces the number of classes to be known beforehand, and makes the system depend on labels to extract concepts. To overcome this limitation, recent work has been proposed that shows how a self-organizing map (SOM) can be used as a completely unsupervised classifier. However, to achieve success it required deep learning techniques to generate high quality embeddings. The purpose of this work is to show that we can use our previously proposed What-Where encoder in tandem with the SOM to get an end-to-end unsupervised system that is Hebbian. Such system, requires no labels to train nor does it require knowledge of which classes exist beforehand. It can be trained online and adapt to new classes that may emerge. As in the original work, we use the MNIST data set to run an experimental analysis and verify that the system achieves similar accuracies to the best ones reported thus far. Furthermore, we extend the analysis to the more difficult Fashion-MNIST problem and conclude that the system still performs.</p>\",\"PeriodicalId\":55374,\"journal\":{\"name\":\"Biological Cybernetics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2023-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10258173/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biological Cybernetics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s00422-023-00963-y\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, CYBERNETICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biological Cybernetics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s00422-023-00963-y","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, CYBERNETICS","Score":null,"Total":0}
Self-organizing maps on "what-where" codes towards fully unsupervised classification.
Interest in unsupervised learning architectures has been rising. Besides being biologically unnatural, it is costly to depend on large labeled data sets to get a well-performing classification system. Therefore, both the deep learning community and the more biologically-inspired models community have focused on proposing unsupervised techniques that can produce adequate hidden representations which can then be fed to a simpler supervised classifier. Despite great success with this approach, an ultimate dependence on a supervised model remains, which forces the number of classes to be known beforehand, and makes the system depend on labels to extract concepts. To overcome this limitation, recent work has been proposed that shows how a self-organizing map (SOM) can be used as a completely unsupervised classifier. However, to achieve success it required deep learning techniques to generate high quality embeddings. The purpose of this work is to show that we can use our previously proposed What-Where encoder in tandem with the SOM to get an end-to-end unsupervised system that is Hebbian. Such system, requires no labels to train nor does it require knowledge of which classes exist beforehand. It can be trained online and adapt to new classes that may emerge. As in the original work, we use the MNIST data set to run an experimental analysis and verify that the system achieves similar accuracies to the best ones reported thus far. Furthermore, we extend the analysis to the more difficult Fashion-MNIST problem and conclude that the system still performs.
期刊介绍:
Biological Cybernetics is an interdisciplinary medium for theoretical and application-oriented aspects of information processing in organisms, including sensory, motor, cognitive, and ecological phenomena. Topics covered include: mathematical modeling of biological systems; computational, theoretical or engineering studies with relevance for understanding biological information processing; and artificial implementation of biological information processing and self-organizing principles. Under the main aspects of performance and function of systems, emphasis is laid on communication between life sciences and technical/theoretical disciplines.