Podcast #3 - Becoming a Kaggle GM + learning AI by OpenSource contribution...
Tanay Mehta is a machine learning engineer and an emerging scientist. He is a self-taught kid who went on all the way to be a Kaggle Grand Master, a feat that remains challenging even for people with several years of experience in the industry. On top of that, in recent years he has made tons of contributions to open-source AI community. That includes a significant contribution to the HuggingFace Transformers library. I have no doubt he is a star in the making in the Machine Learning community.
LINKS FROM THE GUEST
website - https://tanaymehta.com
Github profile - https://github.com/tanaymeh
⌚️ ⌚️ ⌚️ TIMESTAMPS ⌚️ ⌚️ ⌚️
0:00 - Intro
0:47 - Getting started in Machine Learning/Data Science
2:46 - On Kaggle Notebooks GM
6:14 - Cracking Kaggle Competitions
8:55 - Tuning LLM models
11:05 - Dealing with data in Kaggle
14:53 - Models of preference
16:30 - Mamba Model
19:38 - Learning PyTorch on Kaggle
22:40 - Tips on using Notebooks/Colab
26:30 - PyTorch best practices
28:55 - Opensource contributions in AI
31:50 - JAX vs PyTorch
34:00 - Deep Learning Model conversion
36:44 - Starting with Opensource contributions
39:11 - Improving Coding Practices
44:20 - Writing unit tests in python
45:30 - Future of LLMs
47:50 - Keeping up with growth of AI
50:30 - Most happening areas of research
MY KEY LINKS
YouTube: / @aibites
Twitter: / ai_bites
Patreon: / ai_bites
Github: https://github.com/ai-bites
WHO AM I?
I am a Machine Learning researcher/practioner who has seen the grind of academia and start-ups. I started my career as a software engineer 15 years ago. Because of my love for Mathematics (coupled with a glimmer of luck), I graduated with a Master's in Computer Vision and Robotics in 2016 when the now happening AI revolution started. Life has changed for the better ever since.
#machinelearning #deeplearning #aibites