no code implementations • 5 Mar 2021 • Kanthi Sarpatwar, Karthik Nandakumar, Nalini Ratha, James Rayfield, Karthikeyan Shanmugam, Sharath Pankanti, Roman Vaculin
In this work, we propose a framework to transfer knowledge extracted by complex decision tree ensembles to shallow neural networks (referred to as DTNets) that are highly conducive to encrypted inference.
no code implementations • 30 Jan 2021 • Nayna Jain, Karthik Nandakumar, Nalini Ratha, Sharath Pankanti, Uttam Kumar
Using the CKKS scheme available in the open-source HElib library, we show that operational parameters of the chosen FHE scheme such as the degree of the cyclotomic polynomial, depth limitations of the underlying leveled HE scheme, and the computational precision parameters have a major impact on the design of the machine learning model (especially, the choice of the activation function and pooling method).
no code implementations • 20 Aug 2019 • Bishwaranjan Bhattacharjee, John R. Kender, Matthew Hill, Parijat Dube, Siyu Huo, Michael R. Glass, Brian Belgodere, Sharath Pankanti, Noel Codella, Patrick Watson
We use this measure, which we call "Predict To Learn" ("P2L"), in the two very different domains of images and semantic relations, where it predicts, from a set of "source" models, the one model most likely to produce effective transfer for training a given "target" model.
no code implementations • 26 Aug 2017 • Karthikeyan Natesan Ramamurthy, Chung-Ching Lin, Aleksandr Aravkin, Sharath Pankanti, Raphael Viguier
The runtime of our implementation scales linearly with the number of observed points.
no code implementations • 14 Oct 2016 • Noel Codella, Quoc-Bao Nguyen, Sharath Pankanti, David Gutman, Brian Helba, Allan Halpern, John R. Smith
Compared to the average of 8 expert dermatologists on a subset of 100 test images, the proposed system produces a higher accuracy (76% vs. 70. 5%), and specificity (62% vs. 59%) evaluated at an equivalent sensitivity (82%).
no code implementations • CVPR 2014 • Yu Cheng, Quanfu Fan, Sharath Pankanti, Alok Choudhary
Based on this idea, we represent a video by a sequence of visual words learnt from the video, and apply the Sequence Memoizer [21] to capture long-range dependencies in a temporal context in the visual sequence.