{"title":"利用峰值时间相关权重推断克服权重传输问题","authors":"Nasir Ahmad, L. Ambrogioni, M. Gerven","doi":"10.51628/001c.27423","DOIUrl":null,"url":null,"abstract":"We propose a solution to the weight transport problem, which questions the biological plausibility of the backpropagation algorithm. We derive our method based upon a theoretical analysis of the (approximate) dynamics of leaky integrate-and-fire neurons. We show that the use of spike timing alone outcompetes existing biologically plausible methods for synaptic weight inference in spiking neural network models. Furthermore, our proposed method is more flexible, being applicable to any spiking neuron model, is conservative in how many parameters are required for implementation and can be deployed in an online-fashion with minimal computational overhead. These features, together with its biological plausibility, make it an attractive mechanism underlying weight inference at single synapses.","PeriodicalId":74289,"journal":{"name":"Neurons, behavior, data analysis and theory","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2020-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Overcoming the Weight Transport Problem via Spike-Timing-Dependent Weight Inference\",\"authors\":\"Nasir Ahmad, L. Ambrogioni, M. Gerven\",\"doi\":\"10.51628/001c.27423\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a solution to the weight transport problem, which questions the biological plausibility of the backpropagation algorithm. We derive our method based upon a theoretical analysis of the (approximate) dynamics of leaky integrate-and-fire neurons. We show that the use of spike timing alone outcompetes existing biologically plausible methods for synaptic weight inference in spiking neural network models. Furthermore, our proposed method is more flexible, being applicable to any spiking neuron model, is conservative in how many parameters are required for implementation and can be deployed in an online-fashion with minimal computational overhead. These features, together with its biological plausibility, make it an attractive mechanism underlying weight inference at single synapses.\",\"PeriodicalId\":74289,\"journal\":{\"name\":\"Neurons, behavior, data analysis and theory\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-03-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neurons, behavior, data analysis and theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.51628/001c.27423\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurons, behavior, data analysis and theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.51628/001c.27423","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Overcoming the Weight Transport Problem via Spike-Timing-Dependent Weight Inference
We propose a solution to the weight transport problem, which questions the biological plausibility of the backpropagation algorithm. We derive our method based upon a theoretical analysis of the (approximate) dynamics of leaky integrate-and-fire neurons. We show that the use of spike timing alone outcompetes existing biologically plausible methods for synaptic weight inference in spiking neural network models. Furthermore, our proposed method is more flexible, being applicable to any spiking neuron model, is conservative in how many parameters are required for implementation and can be deployed in an online-fashion with minimal computational overhead. These features, together with its biological plausibility, make it an attractive mechanism underlying weight inference at single synapses.