On-device training enables the model to adapt to new data collected from...
Deep neural networks (DNNs) have achieved unprecedented success in the f...
To accelerate CNN inference, existing deep learning frameworks focus on
...
We present Tiny-Transfer-Learning (TinyTL), an efficient on-device learn...
Transformers are ubiquitous in Natural Language Processing (NLP) tasks, ...
Exchanging gradients is a widely used method in modern multi-node machin...
Efficient deep learning computing requires algorithm and hardware co-des...
Neural architecture search (NAS) has a great impact by automatically
des...
Residual learning with skip connections permits training ultra-deep neur...
We propose an approach for forecasting video of complex human activity
i...