Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking.
Haichuan YangYuhao ZhuJi LiuPublished in: ICLR (Poster) (2019)
Keyphrases
- compression ratio
- neural network
- image compression
- data compression
- multi layer
- lossless compression
- multiple layers
- desired output
- pattern recognition
- energy minimization
- fuzzy logic
- sparse data
- high dimensional
- self organizing maps
- output layer
- single layer
- artificial neural networks
- application layer
- back propagation
- multi layer perceptron
- wavelet transform
- neural network model
- feed forward neural networks
- hidden layer
- hidden units
- energy consumption
- genetic algorithm