Talk Abstract:

One of the best things about AI is that you have a lot of open-source content, like open-sourced models, we use them quite frequently. We plan to show how TensorFlow Hub makes this process a lot easier(using models open-sourced) and allows you to seamlessly use pre-trained convolutions or word embeddings in your application. We also plan to show how one can use Transfer Learning on top of these models received from TF Hub, freeze a few layers, and train faster and get much better performance with these. I plan to do have demo example of working with a TF Hub model to show how it works on image data and/or text-based data and how embeddings can be used for your applications

Speaker Bio:

Rishit Dagli is a 10-grade student and is a past TED-X and Ted-Ed speaker. He is an AI and Cloud enthusiast and is also a Google Certified Mobile site developer. He has often represented India in international level Hackathons and competitions and also won a few. He most recently represented the country and won the International Hackathon on Blockchain and IoT by IET. While free, he loves to conduct research and has written 7 research papers in the field of AI and Robotics and Mathematics. He also loves writing technical blogs and has written quite a few of them in the past. With this, he was also awarded the Smartest Techno Kid Award in 2017. He has also given quite a few talks in other communities and colleges. He also was among the top 10 winners for Palo Alto Networking Challenge with GCP. Besides this, he also manages the communities Kotlin Mumbai and Mozilla Mumbai.

Social Media Links

LinkedIn : https://www.linkedin.com/in/rishit-da...
Twitter: https://twitter.com/rishit_dagli
Website: https://www.rishit.tech
GitHub: https://github.com/Rishit-dagli

Thank you.
-- GDG Nashik