About
Avishkar (Avi) Misra, Ph.D.
I am an Inventor, Enabler & Leader in Data Science, Analytics and Artificial Intelligence.
I have built and launched Artificial Intelligence solutions that are used by millions of customers every day.
At Berrijam, I am a founding member of a team that enables people to use artificial intelligence in solving the problems that matter to them, their organization and their community. #NoCodeAI
Previously, I have built products, services, businesses and teams at companies like Microsoft, Amazon, Oracle, Teradata, TracFone/Verizon.
I believe technology is an enabler and should be accessible for all.
Disclaimer: The views and opinions expressed on this site or articles authored by me are my personal views and do not necessarily reflect my current or previous employer's official policy or position.
Expertise
Talks
Democratizing Artificial Intelligence
I M POSSIBLE – CHANGE-Transform India – Future Tech & Sustainability Podcast
Artificial Intelligence For All (AI4All) – An extended conversation with Eddie Avil India on variety of topics including Data Science, AI, GTP3, key-elements to delver on AI, AmazonGo, Deep Learning for Recommendations, and building an equitable and inclusive platform for innovation.
How to deliver on Data Science
Suneratech’s Digital Acceleration Summit 2020
Delivering on the promise of data science is more about culture, processes and empowerment, rather than data, algorithms or technology.
Artificial Intelligence & Machine Learning – Lessons and Opportunities
Teradata Analytical World 2018
Solving data science in business context involves working backwards from the customer or business outcome, challenging tradition, avoiding fashion and getting your solution to production as soon as possible.
ArticlePlant Science Initiative at North Carolina State University
NC State University 2017
Shortening experimentation cycles dramatically scales up the potential to innovate and increase agricultural yields. The College of Agriculture and Life Sciences (CALS) is looking at using Cloud Computing platforms to facilitate collaboration and scaling up Big Data plant science analytics.
ArticlePatents
AmazonGo – retail shopping
AmazonGo is a re-imagining of what a retail shopping experience should look like. My team and I invented new solutions and capabilities. Computer vision, sensors, hardware and artificially intelligent algorithms blend into the background to create a magical shopping experience with AmazonGo.
Precision Agriculture
Combining multi-spectral images (from planes, drone or satellite) with other sensor data can help us measure and track the health of an individual tree in an orchard. Personalizing the water and nutrient at a tree or field level, can lead to higher yields and better quality food.
Internet of Things (IoT) Sensors
IoT sensors when combined with artificial intelligence have a potential to dramatically optimize resources, predict maintenance and reduce theft. Synthesizing high-fidelity time-series sensor signals enables us to maintaining privacy of the IoT sensor locations and customers, while unlocking machine learning innovations.
Papers
THE EFFECTIVENESS OF TWO-LAYER NEURAL NETWORK FOR RECOMMENDATIONS
A less technical overview is provided in:
This neural network classifier algorithm for recommendations that I developed was 2x better than the collaborative filtering algorithms which is has been the heart of Amazon’s product recommendation for decades. The work was described as a “once-in-a-decade leap” by Jeff Wilke.
Oleg Rybakov, Vijai Mohan, Avishkar Misra, Scott LeGrand, Rejith Joseph, Kiuk Chung, Siddharth Singh, Qian You, Eric Nalisnick, Leo Dirac, Runfei Luo
AUTOMATIC LUNG SEGMENTATION: A COMPARISON OF ANATOMICAL AND MACHINE LEARNING APPROACHES
Anatomical landmark detection for image segmentation are time and processing intensive. Machine learning techniques provide significant speed up with minor drop in accuracy. Combining the two can find the best of both worlds.
Avishkar Misra, Mamatha Rudrapatna, Arcot Sowmya
International Conference on Intelligent Sensors, Sensor Networks and Information Processing, 2004 Oleg Rybakov, Vijai Mohan, Avishkar Misra, Scott LeGrand, Rejith Joseph, Kiuk Chung, Siddharth Singh, Qian You, Eric Nalisnick, Leo Dirac, Runfei Luo
INCREMENTAL SYSTEM ENGINEERING USING PROCESS NETWORKS
Avishkar Misra, Arcot Sowmya, Paul Compton
Pacific Knowledge Acquisition Workshop (PKAW), as part of Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2010
ProcessNet allows developers to incrementally develop a very complex vision system using simple image processing techniques and incrementally acquire or discover control and domain knowledge.
Engineering of complex intelligent systems often requires experts to decompose the task into smaller constituent processes. This allows the domain experts to identify and solve specific sub-tasks, which collectively solve the system’s goals. The engineering of individual processes and their relationships represent a knowledge acquisition challenge, which is complicated by incremental ad-hoc revisions that are inevitable in light of evolving data and expertise. Incremental revisions introduce a risk of degrading the system and limit experts’ ability to build complex intelligent systems.
Download PDF
IMPACT OF QUASI-EXPERTISE ON KNOWLEDGE ACQUISITION IN COMPUTER VISION
Avishkar Misra, Arcot Sowmya, Paul Compton
International Conference on Image and Vision Computing, 2009
Too much choice is a bad thing for Quasi-experts. Limiting the options for Quasi-experts by using nominal features and smart binning can reduce the errors in knowledge acquisition by 3 times.
Ripple Down Rules (RDR)’s incremental knowledge acquisition provides computer vision applications with the ability to gradually adapt to the domain and circumvent some of its learning challenges. RDR use incremental exception-based theory revision and rely on the expert to provide the rule conditions. A computer vision expert whilst understanding their significance cannot always provide accurate rule conditions using numeric attributes.
Download PDF
INCREMENTAL LEARNING FOR SEGMENTATION IN MEDICAL IMAGES
Avishkar Misra, Arcot Sowmya, Paul Compton
IEEE International Symposium on Biomedial Imaging, 2006
ProcessRDR reduced the time to develop a computer vision system from 3 months down to 4.5 hours, by adapting incremental knowledge acquisition technique of Ripple Down Rules to the learning of knowledge about controlling image process algorithms.
ISBI 2006 PAPER: PDFPKAW 2004 Workshop: PDF
INCREMENTAL ENGINEERING OF LUNG SEGMENTATION SYSTEMS
Avishkar Misra, Arcot Sowmya, Paul Compton
Pacific Knowledge Acquisition Workshop (PKAW), as part of PacifAyman El-Baz (Editor), Jasjit S. Suri (Editor), Lung Imaging and Computer Aided Diagnosis, CRC Press, ISBN: 439845573, 2011.
ProcessNet made is possible for develop to manage a complex lung anatomy segmentation that segmented seven different anatomical structures building upon each other.
Download PDF