7 citations · 12 across the 3 of their papers we have counts for
5 papers
LayerPipe2: Multistage Pipelining and Weight Recompute via Improved Exponential Moving Average for Training Neural Networks
Nanda K. Unnikrishnan, Keshab K. Parhi
In our prior work, LayerPipe, we had introduced an approach to accelerate training of convolutional, fully connected, and spiking neural networks by overlapping forward and backwar…
SCV-GNN: Sparse Compressed Vector-based Graph Neural Network Aggregation
Nanda K. Unnikrishnan, Joe Gould, Keshab K. Parhi
Graph neural networks (GNNs) have emerged as a powerful tool to process graph-based data in fields like communication networks, molecular interactions, chemistry, social networks,…
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…
LayerPipe: Accelerating Deep Neural Network Training by Intra-Layer and Inter-Layer Gradient Pipelining and Multiprocessor Scheduling
Nanda K. Unnikrishnan, Keshab K. Parhi
The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These…
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…