A Connection Between Score Matching and Denoising Autoencoders

DOI10.1162/NECO_a_00142zbMath1218.68133OpenAlexW2013035813WikidataQ43691963 ScholiaQ43691963MaRDI QIDQ5198602

Pascal Vincent

Publication date: 9 August 2011

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00142

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (11)

Unnamed Item ⋮ Semiactive nonsmooth control for building structure with deep learning ⋮ Image Denoising: The Deep Learning Revolution and Beyond—A Survey Paper ⋮ Deep learning for natural language processing: a survey ⋮ Complex-valued autoencoders ⋮ STDP-Compatible Approximation of Backpropagation in an Energy-Based Model ⋮ Unnamed Item ⋮ Estimation of high-dimensional graphical models using regularized score matching ⋮ A tale of three probabilistic families: Discriminative, descriptive, and generative models ⋮ Unnamed Item ⋮ Learning Finite-Dimensional Coding Schemes with Nonlinear Reconstruction Maps

Cites Work

• Some extensions of score matching
• Training Products of Experts by Minimizing Contrastive Divergence
• Contrastive Divergence in Gaussian Diffusions
• Optimal Approximation of Signal Priors
• A Fast Learning Algorithm for Deep Belief Nets

This page was built for publication: A Connection Between Score Matching and Denoising Autoencoders