Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems.
Jimmy T. H. SmithScott W. LindermanDavid SussilloPublished in: NeurIPS (2021)
Keyphrases
- reverse engineering
- recurrent neural networks
- linear dynamical systems
- dynamical systems
- hidden markov models
- spatio temporal
- real valued
- neural network
- human motion
- software engineering
- dynamic analysis
- feed forward
- video sequences
- echo state networks
- dynamic textures
- artificial neural networks
- object oriented
- gene regulatory networks
- recurrent networks
- program understanding
- latent variable models
- nonlinear dynamic systems
- reverse engineer
- spatial and temporal
- space time
- machine learning
- back propagation
- genetic algorithm