Unsupervised Learning of Initialization in Deep Neural Networks via Maximum Mean Discrepancy.
Cheolhyoung LeeKyunghyun ChoPublished in: CoRR (2023)
Keyphrases
- unsupervised learning
- neural network
- deep architectures
- deep learning
- self organizing maps
- supervised learning
- pattern recognition
- competitive learning
- deep belief networks
- back propagation
- neural nets
- genetic algorithm
- artificial neural networks
- semi supervised
- activation function
- maximum number
- model selection
- fuzzy logic
- machine learning
- dimensionality reduction
- neural network model
- feature selection
- object recognition
- fuzzy systems
- image processing
- training process
- artificial intelligence
- initial conditions
- image segmentation
- feature extraction
- hidden layer
- active learning
- multi layer
- recurrent neural networks
- expert systems
- k means