Unsupervised adaptation for deep neural network using linear least square method.
Roger HsiaoTim NgStavros TsakalidisLong NguyenRichard M. SchwartzPublished in: INTERSPEECH (2015)
Keyphrases
- neural network
- competitive learning
- highly non linear
- unsupervised learning
- deep architectures
- back propagation
- fuzzy logic
- artificial neural networks
- semi supervised
- supervised learning
- data driven
- learning vector quantization
- multi layer
- fuzzy inference system
- pattern recognition
- genetic algorithm
- feed forward
- linear constraints
- activation function
- adaptation process
- neural network model
- network architecture
- training algorithm
- neural nets
- fault diagnosis
- topic models
- machine learning