Zihong Liu, Zhihua Wang, Guolin Li, Zhiping Yu, Chun Zhang
{"title":"在单晶片上连结VLSI与大鼠脊髓神经元的晶片设计方案","authors":"Zihong Liu, Zhihua Wang, Guolin Li, Zhiping Yu, Chun Zhang","doi":"10.1109/CNE.2005.1419578","DOIUrl":null,"url":null,"abstract":"The high complexity of live beings' nervous system determines it's difficult to analyze the working principles of such behaviors as thinking, learning and cognition at molecular level today, i.e. the development of artificial neural networks (ANN) still has to be limited by the understanding of biological neuron networks (BNN). As of now, several studies on neuron-silicon hybrids have been evolved and shown primary success and led to a new emerging multidisciplinary field. In this paper, we propose a novel hybrid neural system chip jointing rat spinal cord neurons and large-scale integrated circuits (VLSI) on a single silicon wafer substrate for fast signal recognition, where three modules are designed and interconnected. Recorded simulations show that combining the individual advantages of BNN and VLSI, the chip will have more intelligent and faster signal processing capabilities as compared with traditional ANN method, especially for fuzzy signals. Moreover, it can also resolve the problems of huge memory space in ANN chips and the high complexity for algorithms","PeriodicalId":113815,"journal":{"name":"Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005.","volume":"61 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Design Proposal for a Chip Jointing VLSI and Rat Spinal Cord Neurons on a Single Silicon Wafer\",\"authors\":\"Zihong Liu, Zhihua Wang, Guolin Li, Zhiping Yu, Chun Zhang\",\"doi\":\"10.1109/CNE.2005.1419578\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The high complexity of live beings' nervous system determines it's difficult to analyze the working principles of such behaviors as thinking, learning and cognition at molecular level today, i.e. the development of artificial neural networks (ANN) still has to be limited by the understanding of biological neuron networks (BNN). As of now, several studies on neuron-silicon hybrids have been evolved and shown primary success and led to a new emerging multidisciplinary field. In this paper, we propose a novel hybrid neural system chip jointing rat spinal cord neurons and large-scale integrated circuits (VLSI) on a single silicon wafer substrate for fast signal recognition, where three modules are designed and interconnected. Recorded simulations show that combining the individual advantages of BNN and VLSI, the chip will have more intelligent and faster signal processing capabilities as compared with traditional ANN method, especially for fuzzy signals. Moreover, it can also resolve the problems of huge memory space in ANN chips and the high complexity for algorithms\",\"PeriodicalId\":113815,\"journal\":{\"name\":\"Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005.\",\"volume\":\"61 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2005-03-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CNE.2005.1419578\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CNE.2005.1419578","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Design Proposal for a Chip Jointing VLSI and Rat Spinal Cord Neurons on a Single Silicon Wafer
The high complexity of live beings' nervous system determines it's difficult to analyze the working principles of such behaviors as thinking, learning and cognition at molecular level today, i.e. the development of artificial neural networks (ANN) still has to be limited by the understanding of biological neuron networks (BNN). As of now, several studies on neuron-silicon hybrids have been evolved and shown primary success and led to a new emerging multidisciplinary field. In this paper, we propose a novel hybrid neural system chip jointing rat spinal cord neurons and large-scale integrated circuits (VLSI) on a single silicon wafer substrate for fast signal recognition, where three modules are designed and interconnected. Recorded simulations show that combining the individual advantages of BNN and VLSI, the chip will have more intelligent and faster signal processing capabilities as compared with traditional ANN method, especially for fuzzy signals. Moreover, it can also resolve the problems of huge memory space in ANN chips and the high complexity for algorithms