Google Vertex AI Hackathon

Welcome to Opening Stream for Google Cloud Vertex AI Hackathon! Join us for opening Talks and Hackathon Guide.

Hackathon Kick-Off

Ksenia Nekrasova and Katharina Beck from Google Cloud will open the Hackathon with inspirational words and onboarding into the Google Cloud products

Google Cloud's Opening

We will guide you through the website, and Discord community - to make sure you will succeed at the Hackathon 

Hackathon Guide

Let's go through the Technology for the Hackathon and how you can get access to it.

Technology and Challenge

Alex Erfurt, the representer of Google Cloud will join the stage to guide you through the AI models and the use cases for your Hackathon projects 

Guide into Google Cloud

After the Kick-Off stream, focus on finding your team for the Hackathon and start brainstorming your idea!

Team Formation time!

5-min tutorial for non-tech participants on the creation of GitHub account

GitHub for non-tech participants

Start of the Team Formation

Join Q&A space on lablab.ai Discord server for open session to discuss any questions you may have

Open Q&A with mentors

Submission Deadline

AutoML

Miyamura80

Manuj

Many ML researchers are unhappy with their development process.

Coding from scratch is laborious since the process for developing and testing new models is largely the same each time but no-code and low-code platforms do not provide enough granularity to tweak models, loss functions, and training processes.

Most ML researchers experiment in Jupyter notebooks. They are quick, composable, and easy to present.However, even with the help of LLMs:
- Copy-pasting code between web-interfaces and notebooks is slow
- Errors in generated code are difficult to detect and fix
- Writing the appropriate prompt to generate correct boilerplate code is still repetitive

Our solution takes existing data and a natural language prompt and uses it to build a model that is compatible with the shape and types of the data. It also uses recursive API calls to fix any errors in the generated code by passing them back to the LLM. In the future, this product could be extended to generate code for the full build, train, test, and measure cycle so that researchers can ask for a set of models to be tested, tweak the generated code as needed, and rapidly evaluate the best model for their needs.

Faster ML Development, Powered by PaLM. 
AutoML Jupyter is more customisable than no-code platforms yet faster than manual coding. It's a VSCode-LLM integration that recursively generates boilerplate code for ML model development and testing.

"AutoML team on Google Vertex AI Hackathon Hackathon"

Team Idea

Submission