Dither is Better than Dropout for Regularising Deep Neural Networks.
Andrew J. R. SimpsonPublished in: CoRR (2015)
Keyphrases
- neural network
- fuzzy logic
- back propagation
- pattern recognition
- artificial neural networks
- neural network model
- genetic algorithm
- feed forward
- transform domain
- error diffusion
- multi layer
- associative memory
- learning rules
- machine learning
- rule extraction
- real time
- fuzzy systems
- deep architectures
- neural nets
- recurrent neural networks
- self organizing maps
- computer simulation
- image quality
- motion estimation
- high quality