Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators.
Malte J. RaschCharles MackinManuel Le GalloAn ChenAndrea FasoliFrédéric OdermattNing LiS. R. NandakumarPritish NarayananHsinyu TsaiGeoffrey W. BurrAbu SebastianVijay NarayananPublished in: CoRR (2023)
Keyphrases
- deep learning
- deep architectures
- restricted boltzmann machine
- computing systems
- unsupervised learning
- ibm power processor
- unsupervised feature learning
- machine learning
- deep belief networks
- computing platform
- computer systems
- real world
- embedded systems
- mental models
- field programmable gate array
- supervised learning
- hardware implementation
- computer vision
- maximum likelihood
- online learning
- weakly supervised
- markov random field
- training set
- training data
- image processing
- central processing unit