Learning representations in Bayesian Confidence Propagation neural networks

被引：7

作者：

Ravichandran, Naresh Balaji ^{[1
]}

Lansner, Anders ^{[2
,3
]}

Herman, Pawel ^{[1
]}

机构：

[1] KTH Royal Inst Technol, Computat Brain Sci Lab, Stockholm, Sweden

[2] Stockholm Univ, Computat Brain Sci Lab, Stockholm, Sweden

[3] KTH Royal Inst Technol, Stockholm, Sweden

来源：

2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2020年

关键词：

neural networks; brain-like computing; bio-inspired; unsupervised learning; structural plasticity; ATTRACTOR NETWORK; MODEL;

D O I：

10.1109/ijcnn48605.2020.9207061

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years. In this work we study biologically inspired unsupervised strategies in neural networks based on local Hebbian learning. We propose new mechanisms to extend the Bayesian Confidence Propagating Neural Network (BCPNN) architecture, and demonstrate their capability for unsupervised learning of salient hidden representations when tested on the MNIST dataset.

引用

页数：7

共 50 条

[41] Bayesian continual learning via spiking neural networks
Skatchkovsky, Nicolas
Jang, Hyeryung
Simeone, Osvaldo
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2022, 16
[42] Learning efficiency of redundant neural networks in Bayesian estimation
Watanabe, S
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (06): : 1475 - 1486
[43] Asymptotics of representation learning in finite Bayesian neural networks*
Zavatone-Veth, Jacob A.
Canatar, Abdulkadir
Ruben, Benjamin S.
Pehlevan, Cengiz
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2022, 2022 (11):
[44] Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
Hernandez-Lobato, Jose Miguel
Adams, Ryan P.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 1861 - 1869
[45] Asymptotics of representation learning in finite Bayesian neural networks
Zavatone-Veth, Jacob A.
Canatar, Abdulkadir
Ruben, Benjamin S.
Pehlevan, Cengiz
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[46] Novel gradient-enhanced Bayesian neural networks for uncertainty propagation
Shi, Yan
Chai, Rui
Beer, Michael
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 429
[47] Hybrid no-propagation learning for multilayer neural networks
Adhikari, Shyam Prasad
Yang, Changju
Slot, Krzysztof
Strzelecki, Michal
Kim, Hyongsuk
NEUROCOMPUTING, 2018, 321 : 28 - 35
[48] Feature Learning and Signal Propagation in Deep Neural Networks
Lou, Yizhang
Mingard, Chris
Hayou, Soufiane
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[49] Orthogonal Transforms For Learning Invariant Representations In Equivariant Neural Networks
Singh, Jaspreet
Singh, Chandan
Rana, Ankur
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 1523 - 1530
[50] Molecular contrastive learning of representations via graph neural networks
Wang, Yuyang
Wang, Jianren
Cao, Zhonglin
Farimani, Amir Barati
NATURE MACHINE INTELLIGENCE, 2022, 4 (03) : 279 - 287

← 1 2 3 4 5 →