Vishal Keshav

I obtained my master's in computer science (AI focus) from University of Massachusetts Amherst and a Bachelor's in Mathematics & Computing from IIT Guwahati.

At Inc., I worked with the internationalization team. Prior to that, at Samsung Research, I worked with on-device AI team on multiple projects involving systems and machine learning for embedded devices.

Posts  /  Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  Twitter

profile photo


project image

Project - Structuring parameter uncertainity for efficient incremental learning

pdf / code /

We exploit the computational structure of convolutions to re-parametrize the weight uncertainty (under the Bayesian framework) in an incremental learning setting. We validate our hypothesis “structured adaptability bias” through empirical experimentations. Our method results in both parameter efficiency and accuracy improvements over state-of-the-art.

project image

Project - Cost aware inference with early exit

pdf / code / slides /

For real-time non-critical continuous machine learning applications, we propose a novel approach to dynamically adjust the model execution time to strike the right balance between accuracy and runtime efficiency. We take advantage of early exit architectures where execution can be halted without losing the final predictions.

project image

Project - Distributed Multi-threaded Map-Reduce Library

pdf / code /

An implementation of the map-reduce protocol in C++. The implementation supports the execution of user-defined map-reduce functions in a distributed environment and ensures fault tolerance.

project image

Paper - Self-supervised visual feature learning with curriculum

paper / code /

Training on a fixed pre-text task has the disadvantage of either letting network take shortcuts or miss semantically valuable information. We take inspiration from the curriculum learning technique to progressively remove low-level signals and show that it significantly increases the speed of convergence of the downstream tasks.

project image

Paper - Decoupling Semantic Context and Color Correlation with Multi-class Cross Branch Regularization

paper / code / poster /

We present a novel design methodology for architecting a light-weight and faster DNN architecture for vision applications. We propose to adopt a multi-branch architecture that decouples pixel level and semantic level signals from an image using efficient point-wise and depth-wise convolution operators. The fused results are then used for global prediction. We achieve computational efficiency by a magnitude of 30x while achieving the same accuracy as state-of-the-art architectures.

project image

Patent - Method and system for DNN based imaging

patent /

The method comprises of simultaneously extracting per-pixel color distribution along the RGB channel dimension and semantic information from each of the color channels, later, fusing the processed signals to output the predictive outcome based on the task.

project image

Patent - Method and system for context based task scheduling in a multi-core processor

patent / patent #2 /

The patents provide methods for managing the execution of tasks by symmetric and asymmetric multi-core processors.

project image

Project - Optimisation of power consumption in wireless network

pdf / code / slides /

This is my Bachelor’s thesis aimed at modeling a wireless network with M/M/1 queue, define a multi-variate power function and apply optimization techniques such as backtrack line search algorithm to minimize the power consumption of the wireless network. We theoretically show the improvements in power consumption given our proposed model.

Other Projects

Side projects and unpublished work can be found on my Github repository here.


Under-construction... please wait...

Design and source code from Jon Barron's website