Last month, Google Bangalore hosted the Workshop on Artificial Intelligence and Machine Learning, with the goal of fostering collaboration between the academic and industry research communities in India. This forum was designed to exchange current research and industry projects in AI & ML, and included faculty and researchers from Indian Institutes of Technology (IITs) and other leading universities in India, along with industry practitioners from Amazon, Delhivery, Flipkart, LinkedIn, Myntra, Microsoft, Ola and many more. Participants spoke on the ongoing research and work being undertaken in India in deep learning, computer vision, natural language processing, systems and generative models (you can access all the presentations from the workshop here).
Google’s Jeff Dean and Prabhakar Raghavan kicked off the workshop by sharing Google’s uses of deep learning to solve challenging problems and reinventing productivity using AI. Additional keynotes were delivered by Googlers Rajen Sheth and Roberto Bayardo. We also hosted a panel discussion on the challenges and future of AI/ML ecosystem in India, moderated by Google Bangalore’s Pankaj Gupta. Panel participants included Anirban Dasgupta (IIT Gandhinagar), Chiranjib Bhattacharyya of the Indian Institute of Science (IISc), Ashish Tendulkar and Srinivas Raaghav (Google India) and Shourya Roy (American Express Big Data Labs).
 |
| Prabhakar Raghavan’s keynote address |
The workshop agenda included five broad sessions with presentations by attendees in the following areas:
- Deep Learning: Balaraman Ravindran (IIT Madras) opened the session discussing the structure in deep reinforcement learning, then Sunita Sarawagi (IIT Bombay) discussed domain generalization via cross-gradient training. Tanuja Ganu (DataGlen Technologies) spoke about creating intelligent and sustainable energy systems and finally Rushi Bhatt (LinkedIn) spoke about maintaining professional quality of the LinkedIn feed using deep learning.
- Natural Language Processing: Sourangshu Bhattacharya (IIT Kharagpur) opened the session talking about task specific representation learning for web-scale entity disambiguation followed by Mausam (IIT Delhi) who delved into hierarchical pointer memory network for task-oriented dialogue. Partha Talukdar (IISc) presented his work on canonicalizing open knowledge graphs then Manish Gupta (VideoKen) discussed his findings in applying machine learning to support human learning. Finally, Arjun Maheshwaran (Agara Labs) and Pankaj Gupta (Google Bangalore) presented their joint-research and industry work on smart customer support.
- Machine Learning Systems: Goda Ramkumar (Ola) opened the session discussing her findings about ML/data science algorithms that power Ola. Prateek Jain (Microsoft Research India) presented his research on resource-efficient ML in 2 KB RAM for the Internet of Things. Animesh Mukherjee (IIT Kharagpur) discussed his yet-to-published work on ranking state-of-the-art papers via incomplete tournaments induced by citations from performance tables. Finally, Srujana Merugu (Independent ML Consultant) provided a practitioner's perspective on building ML Systems.
- Computer Vision: Vineeth Balsubramanian (IIT Hyderabad) opened the session discussing his research on generalized gradient-based visual explanations for deep convolutional networks (Grad-CAM++). Vinay Namboodiri (IIT Kanpur) spoke about his research on adversarial machine learning. Vishnu Makkapati (Myntra) discussed his research and practice in generation of fashion designs using generative adversarial networks. Varun Gulshan (Google Brain) spoke about his research on using ML in medical imaging. Finally, Soma Biswas (IISc) presented her research on preserving semantic similarity for zero-shot learning.
- Reinforcement Learning, Generative Models and more: Aditya Gopalan (IISc) opened the session describing online and reinforcement learning in complex environments. Then Ganesh Ramakrishnan (IIT Bombay) presented research on human assisted machine learning. Lavanya Tekumalla (Amazon) presented her work on using Bayesian models for product size recommendation. Kabir Rustogi (Delhivery) discussed his work on addressing geocoding using graph based machine learning models. Mohit Kumar (Flipkart) presented his research and practice on fraudulent user prediction in ratings platform. The workshop ended with a talk by Rahul Sami (Google) who discussed ML challenges in Google Maps auto-moderation.
 |
| Pankaj Gupta moderating the panel discussion |
As in many countries around the world, we are seeing increased dialog on various aspects of AI and ML in multiple contexts in India. This workshop hosted 80 attendees representing 9 universities and 36 companies contributing 28 excellent talks, with many opportunities for discussing challenges and opportunities for AI/ML in India. Google will continue to foster this exchange of ideas across a diverse set of folks and applications. As part of this, we also announced the upcoming research awards round (applications due June 4) to support up to seven faculty members in India on their AI/ML research, and new work on an accelerator program for Indian entrepreneurs focused primarily on AI/ML technologies. Please keep an eye out for more information about these programs.
