Skip to main navigation
Skip to search
Skip to main content
Technical University of Munich Home
Help & FAQ
Link opens in a new tab
English
Deutsch
Search content at Technical University of Munich
Home
Profiles
Research units
Projects
Research output
Equipment
Prizes
Activities
Press/Media
ResNet with one-neuron hidden layers is a Universal Approximator
Hongzhou Lin
,
Stefanie Jegelka
Massachusetts Institute of Technology
Research output
:
Contribution to journal
›
Conference article
›
peer-review
149
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'ResNet with one-neuron hidden layers is a Universal Approximator'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
ResNet
100%
Hidden Layer
100%
Universal Approximator
100%
Representational Power
50%
Alternating Layers
50%
Identity Mapping
50%
D Dimensions
50%
Dimension One
50%
Fully Connected Network
50%
ReLU Activation Function
50%
Layer Activation
50%
ResNet Architecture
50%
Deep ResNet
50%
Deep Network
50%
Lebesgue Integrable Function
50%
Input Dimension
50%
Multi-stack Module
50%
Mathematics
Hidden Neuron
100%
Resnet
100%
Approximates
25%
One Dimension
25%
Lebesgue Integrable Function
25%
Sharp Contrast
25%
Connected Network
25%
Identity Mapping
25%
Computer Science
Residual Neural Network
100%
Input Dimension
33%
Connected Network
33%
Activation Function
33%
Arts and Humanities
Architecture
100%