activity
20192023
most citedPerformance Analysis of DNN Inference/Training with Convolution and non-Convolution Operations

2 citations · 6 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2022

Accelerating Attention through Gradient-Based Learned Runtime Pruning

Zheng Li, Soroush Ghodrati, Amir Yazdanbakhsh +2

Self-attention is a key enabler of state-of-art accuracy for various transformer-based Natural Language Processing models. This attention mechanism calculates a correlation score f…