Machine Learning India bio photo

Machine Learning India

Fostering science and machine learning in India

Email Mailing List Twitter Github

Are you a student, professor, CEO or Maschinenmensch? Subscribe to ml-india's google group to join the discussion and recieve updates, news and resources about India's ml-ecosystem. Click here

ML India is delighted to inform that the third meet-up in its Gurgaon chapter was held on 21st August 2016.

This time we had a guest speaker Dr. Mayank Vatsa, associate professor and AR Krishnaswamy Faculty Research Fellow at IIIT-Delhi. Mayank received his M.S. and Ph.D. degrees in computer science from West Virginia University, Morgantown, WV, USA, in 2005 and 2008, respectively. Mayank talked about some of the interesting projects that he and the members of his team are undertaking. Mayank walked the members through the projects making the learners understand how to break down the problem and then approach it. He also explained how one should work through the process of collecting the data and implementing it, and then testing different models.

It was a great talk as the students were able to relate to the work and ask multiple questions accordingly. In-between Mayank also explained many concepts of machine learning and the resources that could be helpful in understanding these topics in depth.

Mayank talked about:

  • Face Recognition
  • Finger print recognition
  • Baby Face Recognition (Probably the first ever project in the field)
  • Deep learning applications in image processing
  • Autoencoders

  • After the talk, the QnA session ensued where some questions were around the Mayank’s work and others were around approaching various problems that different participants are facing in their work. Mayank was able to provide significant input. One major discussion was around the hardware selection for deep learning and whether AWS is a better choice to implement the learning algorithms or server boxes are a better choice to go ahead with. The general consensus was on the fact that for testing the architecture, maybe a laptop with decent configuration should work but for final training of the algorithm from the humongous data, a server box with GPU’s should be good.

    The turnout of the meetup was good again with some regular members and some new members joining in the group. The group had participants who were undergraduates, PhD students and machine learning engineers from the corporate sector. Although everyone is working on different subjects, the framewrok falls under one umbrella which make these meetups really interesting.

    We wish Dr. Mayank Vatsa and his team members all the best for the interesting work that they are doing. You can check out more of their work here. We really look forward to having such engaging and interesting meetups, and having researchers and practitioners involved in ML to discuss their work and insights.

    Click here to join the group.

    If you wish to start a chapter of ML-India in your city, we would be more than happy to help you out and get it started. Write us a mail!