首页|A Review of Neuroscience-Inspired Machine Learning
A Review of Neuroscience-Inspired Machine 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-According to news reporting based on a preprint abstract,our journalists obtained the following quote sourced from os f.io: "One major criticism of deep learning centers around the biological implausibili ty of the credit assignment schema used for learning –backpropagation of error s. This implausibility translates into practical limitations,spanning scientifi c fields,including incompatibility with hardware and non-differentiable impleme ntations,thus leading to expensive energy requirements. "In contrast,biologically plausible credit assignment is compatible with practi cally any learning condition and is energy-efficient. "As a result,it accommodates hardware and scientific modeling,e.g. learning wi th physical systems and non-differentiable behavior.
NETL
NSTL
