文献类型：期刊文献

英文题名：Bayesian Pseudoinverse Learners: From Uncertainty to Deterministic Learning

作者：Yin, Qian[1];Xu, Bingxin[2];Zhou, Kaiyan[1];Guo, Ping[3]

第一作者：Yin, Qian

通讯作者：Guo, P[1]

机构：[1]Beijing Normal Univ, Image Proc & Pattern Recognit Lab, Sch Artificial Intelligence, Beijing 100875, Peoples R China;[2]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[3]Beijing Normal Univ, Sch Syst Sci, Image Proc & Pattern Recognit Lab, Beijing 100875, Peoples R China

第一机构：Beijing Normal Univ, Image Proc & Pattern Recognit Lab, Sch Artificial Intelligence, Beijing 100875, Peoples R China

通讯机构：[1]corresponding author), Beijing Normal Univ, Sch Syst Sci, Image Proc & Pattern Recognit Lab, Beijing 100875, Peoples R China.

年份：2022

卷号：52

期号：11

起止页码：12205-12216

外文期刊名：IEEE TRANSACTIONS ON CYBERNETICS

收录：;EI(收录号：20212310473118);Scopus(收录号：2-s2.0-85107389079);WOS:【SCI-EXPANDED(收录号:WOS:000732371700001)】；

基金：This work was supported in part by the National Key Research and Development Program of China under Grant 2018AAA0100203; in part by the National Natural Science Foundation of China under Grant 62006020; and in part by the Joint Research Fund in Astronomy under cooperative agreement between the National Natural Science Foundation of China (NSFC) and Chinese Academy of Sciences (CAS) under Grant U2031136.

语种：英文

外文关键词：Uncertainty; Modeling; Computational modeling; Probabilistic logic; Neural networks; Bayes methods; Task analysis; Bayesian; feedforward neural networks; mixture priors; pseudoinverse learners (PILs); synergetic learning

摘要：Pseudo-inverse learners (PILs) are a kind of feedforward neural network trained with the pseudoinverse learning algorithm, which can be traced back to 1995 originally. PIL is an approach for nongradient descent learning, and its main advantage is the lower computational cost and fast learning procedure, which is especially relevant in the edge computing research field. However, PIL is mostly applied to a deterministic learning problem, while in the real world, the greatest case that is of concern is the uncertainty learning problem. In this work, under the framework of the synergetic learning system (SLS), we introduce an approximated synergetic learning scheme, which can transform uncertainty learning into deterministic learning. We call this new learning framework the Bayesian PIL, and the advantages are also demonstrated in this work.