Asymptotics of representation learning in finite Bayesian neural networks.
Jacob A. Zavatone-VethAbdulkadir CanatarBenjamin S. RubenCengiz PehlevanPublished in: NeurIPS (2021)
Keyphrases
- neural network
- learning process
- learning algorithm
- pattern recognition
- supervised learning
- prior knowledge
- genetic algorithm
- learning capabilities
- bayesian learning
- image representation
- artificial neural networks
- bayesian networks
- active learning
- sufficient conditions
- unsupervised learning
- expert systems
- learning tasks
- learning rules
- reinforcement learning
- feedforward neural networks
- multiple representations
- error back propagation
- cascade correlation