MétaCan
← all works

Reducing the Dimensionality of Data with Neural Networks

2006· article· en· 20,953 citations· W2100495367 on OpenAlex· 10.1126/science.1127647

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

Abstract

High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such "autoencoder" networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

The record

Venue
Science
Topic
Neural Networks and Applications
Field
Computer Science
Canadian institutions
University of TorontoUniversity of New Brunswick
Funders
Keywords
AutoencoderCurse of dimensionalityInitializationGradient descentArtificial neural networkComputer sciencePrincipal component analysisArtificial intelligencePattern recognition (psychology)Layer (electronics)High dimensionalPrincipal (computer security)AlgorithmMaterials scienceNanotechnology
Has abstract in OpenAlex
yes