Adaptive Block Floating-Point for Analog Deep Learning Hardware.
Ayon BasumallikDarius BunandarNicholas DronenNicholas C. HarrisLudmila LevkovaCalvin McCarterLakshmi NairDavid WalterDavid WidemannPublished in: CoRR (2022)
Keyphrases
- floating point
- deep learning
- floating point arithmetic
- instruction set
- unsupervised learning
- fixed point
- floating gate
- unsupervised feature learning
- weakly supervised
- floating point unit
- mental models
- machine learning
- hardware and software
- low cost
- signal processing
- general purpose
- image processing
- computer systems
- data mining
- active learning
- feature selection
- computer vision