activity
20172022
most citedGabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks

79 citations · 95 across the 4 of their papers we have counts for

collaborators

5 papers

cs.AR2022

Distributed On-Sensor Compute System for AR/VR Devices: A Semi-Analytical Simulation Framework for Power Estimation

Jorge Gomez, Saavan Patel, Syed Shakib Sarwar +8

Augmented Reality/Virtual Reality (AR/VR) glasses are widely foreseen as the next generation computing platform. AR/VR glasses are a complex "system of systems" which must satisfy…

cs.LG202216 cited

Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks

Dominika Przewlocka-Rus, Syed Shakib Sarwar, H. Ekin Sumbul +2

Deploying Deep Neural Networks in low-power embedded devices for real time-constrained applications requires optimization of memory and computational complexity of the networks, us…

cs.NE2019

A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks

Saima Sharmin, Priyadarshini Panda, Syed Shakib Sarwar +3

In this era of machine learning models, their functionality is being threatened by adversarial attacks. In the face of this struggle for making artificial neural networks robust, f…

cs.NE2019

Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures

Chankyu Lee, Syed Shakib Sarwar, Priyadarshini Panda +2

Spiking Neural Networks (SNNs) have recently emerged as a prominent neural computing paradigm. However, the typical shallow SNN architectures have limited capacity for expressing c…

cs.NE201779 cited

Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks

Syed Shakib Sarwar, Priyadarshini Panda, Kaushik Roy

Convolutional Neural Networks (CNN) are being increasingly used in computer vision for a wide range of classification and recognition problems. However, training these large networ…