activity
20122021
most citedGabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks

79 citations · 495 across the 38 of their papers we have counts for

collaborators
Showing 2018Show all

13 papers · 1 filter

cs.CV2018

A Low Effort Approach to Structured CNN Design Using PCA

Isha Garg, Priyadarshini Panda, Kaushik Roy

Deep learning models hold state of the art performance in many fields, yet their design is still based on heuristics or grid search methods that often result in overparametrized ne…

cs.ET2018

RxNN: A Framework for Evaluating Deep Neural Networks on Resistive Crossbars

Shubham Jain, Abhronil Sengupta, Kaushik Roy +1

Resistive crossbars designed with non-volatile memory devices have emerged as promising building blocks for Deep Neural Network (DNN) hardware, due to their ability to compactly an…

cs.ET2018

A Photonic In-Memory Computing primitive for Spiking Neural Networks using Phase-Change Materials

Indranil Chakraborty, Gobinda Saha, Kaushik Roy

Spiking Neural Networks (SNNs) offer an event-driven and more biologically realistic alternative to standard Artificial Neural Networks based on analog information processing. This…

cs.LG2018

Implicit Generative Modeling of Random Noise during Training for Adversarial Robustness

Priyadarshini Panda, Kaushik Roy

We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative mod…

cs.ET2018

Xcel-RAM: Accelerating Binary Neural Networks in High-Throughput SRAM Compute Arrays

Amogh Agrawal, Akhilesh Jaiswal, Deboleena Roy +4

Deep neural networks are a biologically-inspired class of algorithms that have recently demonstrated state-of-the-art accuracies involving large-scale classification and recognitio…

cs.ET2018

Exploiting Inherent Error-Resiliency of Neuromorphic Computing to achieve Extreme Energy-Efficiency through Mixed-Signal Neurons

Baibhab Chatterjee, Priyadarshini Panda, Shovan Maity +3

Neuromorphic computing, inspired by the brain, promises extreme efficiency for certain classes of learning tasks, such as classification and pattern recognition. The performance an…