I lead the Retail and Distribution team in the Industries Research group at IBM Research, India.
My background is in machine learning and deep learning with a focus on crafting architectures for novel text and image understanding tasks.
I have good domain expertise in fashion and retail and am able to understand the business requirements from various stake holders and translate it to AI modules and research problems.
In the academic community I am well known for my research work on crowdsourcing and learning with imperfect supervision.
From my earlier work I also have a good understanding of health care business with a focus on medical imaging.
Technical lead for the IBM Research AI for Fashion – The IBM Research AI for Fashion project has built a portfolio of APIs, assets, and use cases for the fashion and retail industry primarily leveraging deep learning, computer vision and natural language processing. The use cases are targeted towards end consumers, online retailers, buyers, merchandisers and designers and spans sell (front end customer experience), buy (back end merchandising and procurement) and creative design (fashion designers).
2015-2016 Technical lead for the LingVist: The Far Reaching Research project LingVist: A picture is worth a thousand words aims to build a cognitive system that given an image can automatically and concisely summarize the salient content in the image in a few descriptive sentences.
2012-2015 Technical lead from India for Project Debater -Project Debater is the first AI system that can debate humans on complex topics. It digests massive texts, constructs a well-structured speech on a given topic, delivers it with clarity and purpose, and rebuts its opponent. Eventually, it will help people reason by providing compelling, evidence-based arguments and limiting the influence of emotion, bias, or ambiguity.