Omesh Tickoo

Principal Engineer and Research Manager in Intel Labs

Research Areas

  • Algorithms

  • Architecture

  • Artificial Intelligence (AI)

  • Autonomous Driving

  • Client SoC

  • Cloud Computing Systems

  • Cognitive Computing

  • Computer Vision

  • Data Analytics & Modeling

  • Distributed Systems

  • Edge Computing

  • Low Power

  • Machine Learning

  • Media Processing

  • Multi-Modal Sensemaking

  • Networking

  • Reinforcement Learning (RL)

  • Robotics

  • SoC & IP Architecture and Design

  • System Architecture & Integration

  • Visual Computing System

  • x86 Instruction Set Architecture



Omesh’s current research interests include probabilistic computing, interactive multi-modal scene understanding and contextual learning. In the past Omesh has worked on projects related to low power hardware acceleration, contextual knowledge management and systems optimization for different Intel platform solutions.

Omesh received his PhD from Rensselaer Polytechnic Institute for his thesis on Analysis and Improvement of Multimedia Transmission over Wireless Networks. Omesh has authored more than 30 papers in premier international Journals and Conferences and holds about 30 patents. Omesh has served as chair of multiple committees for IEEE conferences. He has co-organized Computational Intelligence and Soft Computing workshops alongside PACT. Omesh regularly serves as a Technical Program Committee member and reviewer for international conferences and journals.

Blogs & Publications

Specifying weight priors in Bayesian Deep Neural Networks with Empirical Bayes
AAAI Conference on Artificial Intelligence 2020, 2/7/2020

Improving MFVI in Bayesian Neural Networks with Empirical Bayes: a Study with Diabetic Retinopathy Diagnosis
NeurIPS 2019 Bayesian Deep Learning workshop, 12/13/2019

Adaptive Activation Functions Using Fractional Calculus
ICCV, 11/3/2019