Sparse progressive distillation: Resolving overfitting under pretrain-and-finetune paradigm
Conventional wisdom in pruning Transformer-based language models is that pruning
reduces the model expressiveness and thus is more likely to underfit rather than overfit …
reduces the model expressiveness and thus is more likely to underfit rather than overfit …
Binary complex neural network acceleration on fpga
Being able to learn from complex data with phase information is imperative for many signal
processing applications. Today's real-valued deep neural networks (DNNs) have shown …
processing applications. Today's real-valued deep neural networks (DNNs) have shown …
Optimizing fpga-based accelerator design for large-scale molecular similarity search (special session paper)
Molecular similarity search has been widely used in drug discovery to identify structurally
similar compounds from large molecular databases rapidly. With the increasing size of …
similar compounds from large molecular databases rapidly. With the increasing size of …