Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network

DOI10.1162/089976603762552988MaRDI QIDQ4408946zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Xiaohui Xie, H. Sebastian Seung

Publication date 2003

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/089976603762552988

zbMATH Keywords

training networks with hidden neurons

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A HETEROSYNAPTIC LEARNING RULE FOR NEURAL NETWORKS
• Dense Hebbian neural networks: a replica symmetric picture of supervised learning
• Dense Hebbian neural networks: a replica symmetric picture of unsupervised learning
• Hebbian Learning of Recurrent Connections: A Geometrical Perspective
• Complex Functional Network Hebbian-Type Learning Algorithm and Convergence
• On the Asymptotic Equivalence Between Differential Hebbian and Temporal Difference Learning
• Equivalence of equilibrium propagation and recurrent backpropagation

Cites work

• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• Learning representations by back-propagating errors
• Neurons with graded response have collective computational properties like those of two-state neurons

Cited in

(14)

• Learning in the machine: the symmetries of the deep learning channel
• Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations
• Generalization in interactive networks: The benefits of inhibitory competition and Hebbian learning
• Backpropagation
• Equivalence of equilibrium propagation and recurrent backpropagation
• A predictive-coding network that is both discriminative and generative
• Contrastive similarity matching for supervised learning
• Predictive coding, variational autoencoders, and biological connections
• Why do similarity matching objectives lead to Hebbian/anti-Hebbian networks?
• A learning framework for winner-take-all networks with stochastic synapses
• Learning representations by back-propagating errors
• An approximation of the error backpropagation algorithm in a predictive coding network with local Hebbian synaptic plasticity
• Neural net backlash compensation with Hebbian tuning using dynamic inversion
• Equilibrium propagation: the quantum and the thermal cases

This page was built for publication: Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4408946)