Memorizing Gaussians with no over-parameterizaion via gradient decent on neural networks.
Amit DanielyPublished in: CoRR (2020)
Keyphrases
- neural network
- linear combination
- pattern recognition
- fuzzy logic
- back propagation
- artificial neural networks
- mixture model
- recurrent neural networks
- training algorithm
- multilayer perceptron
- neural nets
- mixture of gaussians
- fuzzy neural network
- network architecture
- probability density function
- edge detection
- reinforcement learning
- genetic algorithm