A simple connection from loss flatness to compressed representations in neural networks.
Shirui ChenStefano RecanatesiEric Shea-BrownPublished in: CoRR (2023)
Keyphrases
- neural network
- distributed representations
- hopfield neural network
- data structure
- feature selection
- website
- reinforcement learning
- pattern recognition
- computational complexity
- expert systems
- artificial neural networks
- query processing
- higher level
- fault diagnosis
- self organizing maps
- feed forward
- data compression
- artificial intelligence
- highly reliable
- database