Search: id:"swepub:oai:DiVA.org:kth-292966" >
Learning representa...
Learning representations in Bayesian Confidence Propagation neural networks
-
- Ravichandran, Naresh Balaji (author)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST),Computat Brain Sci Lab
-
- Lansner, Anders, Professor (author)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST),Computat Brain Sci Lab
-
- Herman, Pawel, 1979- (author)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST),Computat Brain Sci Lab
-
(creator_code:org_t)
- IEEE, 2020
- 2020
- English.
-
In: 2020 International joint conference on neural networks (IJCNN). - : IEEE.
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- 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.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Keyword
- neural networks
- brain-like computing
- bio-inspired
- unsupervised learning
- structural plasticity
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database