Quantization of Deep Neural Networks to facilitate self-correction of weights on Phase Change Memory-based analog hardware.
Arseni IvanovPublished in: CoRR (2023)
Keyphrases
- neural network
- vlsi architecture
- pattern recognition
- circuit design
- low cost
- real time
- error detection
- neural network model
- digital circuits
- artificial neural networks
- hardware and software
- digital computer
- linear combination
- knowledge retrieval
- fuzzy logic
- vlsi implementation
- multi layer
- hardware implementation
- back propagation
- computer systems
- signal processing
- network architecture
- weighted sum
- training phase
- recurrent neural networks
- color quantization
- weight update
- multiresolution
- frequency modulation
- neural nets
- quantization error
- low power
- associative memory
- successive approximation