首页|University of Otago Researcher Reports on Findings in Neural Computation (Protot ype Analysis in Hopfield Networks with Hebbian Learning)
University of Otago Researcher Reports on Findings in Neural Computation (Protot ype Analysis in Hopfield Networks with Hebbian Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on neural comput ation have been published. According to news reporting originating from the Univ ersity of Otago by NewsRx correspondents, research stated, “We discuss prototype formation in the Hopfield network. Typically, Hebbian learning with highly corr elated states leads to degraded memory performance.” Our news correspondents obtained a quote from the research from University of Ot ago: “We show that this type of learning can lead to prototype formation, where unlearned states emerge as representatives of large correlated subsets of states , alleviating capacity woes. This process has similarities to prototype learning in human cognition. We provide a substantial literature review of prototype lea rning in associative memories, covering contributions from psychology, statistic al physics, and computer science. We analyze prototype formation from a theoreti cal perspective and derive a stability condition for these states based on the n umber of examples of the prototype presented for learning, the noise in those ex amples, and the number of nonexample states presented. The stability condition i s used to construct a probability of stability for a prototype state as the fact ors of stability change. We also note similarities to traditional network analys is, allowing us to find a prototype capacity. We corroborate these expectations of prototype formation with experiments using a simple Hopfield network with sta ndard Hebbian learning.”
University of OtagoComputationEmergi ng TechnologiesHopfield NetworksMachine LearningNeural Computation
NETL
NSTL
