Search Results for author: Deboleena Roy

Found 7 papers, 2 papers with code

On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars

no code implementations19 Sep 2021 Deboleena Roy, Chun Tao, Indranil Chakraborty, Kaushik Roy

First, we study the noise stability of such networks on unperturbed inputs and observe that internal activations of adversarially trained networks have lower Signal-to-Noise Ratio (SNR), and are sensitive to noise than vanilla networks.

On the Intrinsic Robustness of NVM Crossbars Against Adversarial Attacks

no code implementations27 Aug 2020 Deboleena Roy, Indranil Chakraborty, Timur Ibrayev, Kaushik Roy

The increasing computational demand of Deep Learning has propelled research in special-purpose inference accelerators based on emerging non-volatile memory (NVM) technologies.

Image Generation

Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence

1 code implementation4 Jun 2019 Indranil Chakraborty, Deboleena Roy, Isha Garg, Aayush Ankit, Kaushik Roy

The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles.

Autonomous Vehicles Dimensionality Reduction +4

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

no code implementations24 May 2019 Deboleena Roy, Priyadarshini Panda, Kaushik Roy

The spiking autoencoders are benchmarked on MNIST and Fashion-MNIST and achieve very low reconstruction loss, comparable to ANNs.

Image Generation

Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge

no code implementations1 Feb 2019 Indranil Chakraborty, Deboleena Roy, Aayush Ankit, Kaushik Roy

In this work, we propose extremely quantized hybrid network architectures with both binary and full-precision sections to emulate the classification performance of full-precision networks while ensuring significant energy efficiency and memory compression.

Edge-computing Quantization

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

no code implementations1 Jul 2018 Amogh Agrawal, Akhilesh Jaiswal, Deboleena Roy, Bing Han, Gopalakrishnan Srinivasan, Aayush Ankit, Kaushik Roy

In this paper, we demonstrate how deep binary networks can be accelerated in modified von-Neumann machines by enabling binary convolutions within the SRAM array.

Emerging Technologies

Tree-CNN: A Hierarchical Deep Convolutional Neural Network for Incremental Learning

1 code implementation15 Feb 2018 Deboleena Roy, Priyadarshini Panda, Kaushik Roy

Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks.

Fine-tuning Incremental Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.