activity
20202025
most citedLayerPipe: Accelerating Deep Neural Network Training by Intra-Layer and Inter-Layer Gradient Pipelining and Multiprocessor Scheduling

11 citations · 28 across the 5 of their papers we have counts for

collaborators
Showing eess.SPShow all

2 papers · 1 filter

eess.SP2022★ 7 cited

Multi-Channel FFT Architectures Designed via Folding and Interleaving

Nanda K. Unnikrishnan, Keshab K. Parhi

Computing the FFT of a single channel is well understood in the literature. However, computing the FFT of multiple channels in a systematic manner has not been fully addressed. Thi…

eess.SP2020★ 5 cited

A Gradient-Interleaved Scheduler for Energy-Efficient Backpropagation for Training Neural Networks

Nanda Unnikrishnan, Keshab K. Parhi

This paper addresses design of accelerators using systolic architectures for training of neural networks using a novel gradient interleaving approach. Training the neural network i…