activity
20192023
most citedFastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network

97 citations · 156 across the 6 of their papers we have counts for

collaborators

8 papers

cs.HC202246 cited

ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Users

Dhruv Jain, Khoa Huynh Anh Nguyen, Steven Goodman +7

Recent advances have enabled automatic sound recognition systems for deaf and hard of hearing (DHH) users on mobile devices. However, these tools use pre-trained, generic sound rec…

cs.CV20213 cited

Disrupting Model Training with Adversarial Shortcuts

Ivan Evtimov, Ian Covert, Aditya Kusupati +1

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventabl…

cs.LG2021

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan +6

Learning binary representations of instances and classes is a classical problem with several high potential applications. In modern settings, the compression of high-dimensional ne…

cs.CV2020

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

Oindrila Saha, Aditya Kusupati, Harsha Vardhan Simhadri +2

Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps. These require large working memory and are thus un…

cs.LG2020

Soft Threshold Weight Reparameterization for Learnable Sparsity

Aditya Kusupati, Vivek Ramanujan, Raghav Somani +4

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform…

cs.LG202010 cited

Extreme Regression for Dynamic Search Advertising

Yashoteja Prabhu, Aditya Kusupati, Nilesh Gupta +1

This paper introduces a new learning paradigm called eXtreme Regression (XR) whose objective is to accurately predict the numerical degrees of relevance of an extremely large numbe…