activity
20122019
most citedGabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks

79 citations · 251 across the 17 of their papers we have counts for

collaborators

19 papers

cs.ET201921 cited

X-CHANGR: Changing Memristive Crossbar Mapping for Mitigating Line-Resistance Induced Accuracy Degradation in Deep Neural Networks

Amogh Agrawal, Chankyu Lee, Kaushik Roy

There is widespread interest in emerging technologies, especially resistive crossbars for accelerating Deep Neural Networks (DNNs). Resistive crossbars offer a highly-parallel and…

physics.comp-ph20192 cited

Non-equilibrium Green's Function and First Principle Approach to Modeling of Multiferroic Tunnel Junctions

Robert Andrawis, Kaushik Roy

Recently, multiferroic tunnel junctions (MFTJs) have gained significant spotlight in the literature due to its high tunneling electro-resistance together with its non-volatility. I…

cs.LG2019

PABO: Pseudo Agent-Based Multi-Objective Bayesian Hyperparameter Optimization for Efficient Neural Accelerator Design

Maryam Parsa, Aayush Ankit, Amirkoushyar Ziabari +1

The ever increasing computational cost of Deep Neural Networks (DNN) and the demand for energy efficient hardware for DNN acceleration has made accuracy and hardware cost co-optimi…

cs.LG2019

Reinforcement Learning with Low-Complexity Liquid State Machines

Wachirawit Ponghiran, Gopalakrishnan Srinivasan, Kaushik Roy

We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very li…

cs.NE2019

Synthesizing Images from Spatio-Temporal Representations using Spike-based Backpropagation

Deboleena Roy, Priyadarshini Panda, Kaushik Roy

Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic…

cs.NE2019

Evaluating the Stability of Recurrent Neural Models during Training with Eigenvalue Spectra Analysis

Priyadarshini Panda, Efstathia Soufleri, Kaushik Roy

We analyze the stability of recurrent networks, specifically, reservoir computing models during training by evaluating the eigenvalue spectra of the reservoir dynamics. To circumve…