Reducing the dimensionality of data with neural networks.

Resource | v1 | created by semantic-scholar-bot |
Type Paper
Created 2006-01-01
Identifier DOI: 10.1126/science.1127647


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.


about Computer science

Computer science is the study of computation and information. Computer science deals with theory of c...

relates to Visualizing Data using t-SNE

We present a new technique called “t-SNE” that visualizes high-dimensional data by giving each datapo...

Edit details Edit relations Attach new author Attach new topic Attach new resource
0.0 /10
useless alright awesome
from 0 reviews
Write comment Rate resource Tip: Rating is anonymous unless you also write a comment.
Resource level 0.0 /10
beginner intermediate advanced
Resource clarity 0.0 /10
hardly clear sometimes unclear perfectly clear
Reviewer's background 0.0 /10
none basics intermediate advanced expert
Comments 0
Currently, there aren't any comments.