首页|Agency for Science Researcher Provides New Insights into Boltzmann Machines (Effect of stochastic activation function on reconstruction performance of restricted Boltzmann machines with stochastic magnetic tunnel junctions)
Agency for Science Researcher Provides New Insights into Boltzmann Machines (Effect of stochastic activation function on reconstruction performance of restricted Boltzmann machines with stochastic magnetic tunnel junctions)
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
New research on Boltzmann machines is the subject of a new report. According to news originating from the Agency for Science by NewsRx correspondents, research stated, “Stochastic Magnetic Tunnel Junctions (SMTJs) emerge as a promising candidate for neuromorphic computing.” Financial supporters for this research include Agency For Science, Technology And Research. The news journalists obtained a quote from the research from Agency for Science: “The inherent stochasticity of SMTJs makes them ideal for implementing stochastic synapses or neurons in neuromorphic computing. However, the stochasticity of SMTJs may impair the performance of neuromorphic systems. In this study, we conduct a systematic examination of the influence of three stochastic effects (shift, change of slope, and broadening) on the sigmoid activation function. We further explore the implications of these effects on the reconstruction performance of Restricted Boltzmann Machines (RBMs). We find that the trainability of RBMs is robust against the three stochastic effects. However, reconstruction error is strongly related to the three stochastic effects in SMTJs-based RBMs.”
Agency for ScienceBoltzmann MachineEmerging TechnologiesMachine Learning