尖峰神经网络
神经形态工程学
计算机科学
人工神经网络
人工智能
推论
贝叶斯推理
光子学
贝叶斯概率
特征(语言学)
无监督学习
模式识别(心理学)
机器学习
物理
光学
哲学
语言学
作者
Bowen Ma,Junfeng Zhang,Xing Li,Weiwen Zou
出处
期刊:Optics Letters
[The Optical Society]
日期:2023-03-06
卷期号:48 (6): 1411-1411
被引量:3
摘要
Stochasticity is an inherent feature of biological neural activities. We propose a noise-injection scheme to implement a GHz-rate stochastic photonic spiking neuron (S-PSN). The firing-probability encoding is experimentally demonstrated and exploited for Bayesian inference with unsupervised learning. In a breast diagnosis task, the stochastic photonic spiking neural network (S-PSNN) can not only achieve a classification accuracy of 96.6%, but can also evaluate the diagnosis uncertainty with prediction entropies. As a result, the misdiagnosis rate is reduced by 80% compared to that of a conventional deterministic photonic spiking neural network (D-PSNN) for the same task. The GHz-rate S-PSN endows the neuromorphic photonics with high-speed Bayesian inference for reliable information processing in error-critical scenarios.
科研通智能强力驱动
Strongly Powered by AbleSci AI