Join the GDG AI for Science for a hands-on workshop designed specifically for researchers, scientists, and students who want to learn how to leverage the Kaggle platform for data-driven discovery. Kaggle is a rich ecosystem for accessing highly-curated, domain-specific datasets, collaborating in notebooks, leveraging free cloud GPU resources, and, as a bonus, offers competitions to test your workflows and skills and win cash prizes.

This workshop will demystify the process of participating in a data science competition and catalyse the Kaggle ecosystem for your research. We will work with CSIRO's live competition Image2Biomass, tackling a real-world scientific imaging challenge to help farmers estimate feed for livestock.

Expect a practical, end-to-end walkthrough as we work directly within Kaggle Notebooks to build, train, and submit a solution. This session is designed to give you a complete framework you can apply to future competitions and your own research work.

Participants will gain a practical understanding of:

• Navigating the Kaggle Ecosystem: You'll learn how to effectively find, fork, and manage Kaggle notebooks and datasets for your own research.

• Modern AI for Image Segmentation: You'll learn fundamental AI/ML approaches in Python for image-based prediction.

• The End-to-End Competition Workflow: You'll get practical experience with the entire process, from exploring the data and building a baseline model to generating a valid submission file.

• Making Your First Submission: You'll gain the confidence to officially join the competition, submit your results to the live leaderboard, and understand how to iterate and improve your score.

The course will be all hands-on exercises and live-coding demonstrations to reinforce your learning and build confidence.

Requirements:

1. A Kaggle account (use your Google credentials to sign up/login at https://www.kaggle.com/). Note: to use GPU accelerators your account must be verified with a phone number.

2. Basic familiarity with Python is recommended, we will walk through the basics and extend fundamental Python toward AI, ML, and Data Science skills.

3. A steady internet connection to join the two-hour Google Meet.

Content:

1st Hour

• Overview of Kaggle

• Overview of the competition: https://www.kaggle.com/competitions/csiro-biomass

• Submit your first Notebook - great intro here: https://www.kaggle.com/code/krabhijeet/csiro-image2biomass-submission
  

2nd Hour

• Advanced Notebook: coming soon!

• Discussion by competition experts