Skip to main navigation
Skip to search
Skip to main content
Israeli Research Community Portal Home
Help & FAQ
Home
Profiles
Research units
Research output
Search by expertise, name or affiliation
Opening the black box: Low-dimensional dynamics in high-dimensional recurrent neural networks
David Sussillo,
Omri Barak
Research output
:
Contribution to journal
›
Article
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Opening the black box: Low-dimensional dynamics in high-dimensional recurrent neural networks'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Recurrent Neural Network
100%
Open the Black Box
100%
Low-dimensional Dynamics
100%
Linearization
28%
Linearized Dynamics
28%
Two-point
14%
Phase Space
14%
Slow Movement
14%
Optimization Techniques
14%
Bit-flipping
14%
Black Box
14%
Nonlinear Relationship
14%
Moving Average
14%
Flip-flop
14%
3-bits
14%
Dependent Inputs
14%
Crucial Aspect
14%
Time-varying Inputs
14%
Temporal Dependence
14%
Sine Wave Generator
14%
Mathematics
Neural Network
100%
Black Box
100%
Fixed Point
28%
Phase Space
14%
Wide Variety
14%
Nonlinear Relationship
14%
Moving Average
14%
Sine Wave
14%
Engineering
Black Box
100%
Recurrent Neural Network
100%
Fixed Point
28%
Phase Space
14%
Illustrates
14%
Optimization Technique
14%
Moving Average
14%
Flip Flop Circuits
14%
Neuroscience
Recurrent Neural Network
100%
Behavior (Neuroscience)
14%
Chemical Engineering
Recurrent Neural Network
100%
Economics, Econometrics and Finance
Smoothing Technique
100%