Synaptic Sampling of Neural Networks.
CoRR(2023)
摘要
Probabilistic artificial neural networks offer intriguing prospects for
enabling the uncertainty of artificial intelligence methods to be described
explicitly in their function; however, the development of techniques that
quantify uncertainty by well-understood methods such as Monte Carlo sampling
has been limited by the high costs of stochastic sampling on deterministic
computing hardware. Emerging computing systems that are amenable to
hardware-level probabilistic computing, such as those that leverage stochastic
devices, may make probabilistic neural networks more feasible in the
not-too-distant future. This paper describes the scANN technique --
\textit{sampling (by coinflips) artificial neural networks} -- which enables
neural networks to be sampled directly by treating the weights as Bernoulli
coin flips. This method is natively well suited for probabilistic computing
techniques that focus on tunable stochastic devices, nearly matches fully
deterministic performance while also describing the uncertainty of correct and
incorrect neural network outputs.
更多查看译文
关键词
probabilistic computing,artificial neural networks,Bayesian neural networks,neuromorphic computing
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要