Everybody is talking about (and with) ChatGPT. I tried it and was impressed by how well the language model behaves and finally how real and humanly it appears, despite the obvious nonsense that it outputs. I was wondering how machine learning practically works and how to build a neural network.

Project Description

Learn about AI, ML, neural networks and get a better idea on limitations, risks and opportunities.

Goal for this Hackweek

Understand the concepts, create a demo case for machine learning with OS software.

Resources

Needs time in the first place to view documentation, and probably a Cray EX235a towards the end of the week :-)

Looking for hackers with the skills:

ai artificial-intelligence ml machine-learning neural

This project is part of:

Hack Week 22

Activity

  • over 2 years ago: maritawerner joined this project.
  • over 2 years ago: fgiudici liked this project.
  • over 2 years ago: robert.richardson liked this project.
  • over 2 years ago: maritawerner liked this project.
  • over 2 years ago: rsimai started this project.
  • over 2 years ago: rsimai added keyword "ml" to this project.
  • over 2 years ago: rsimai added keyword "machine-learning" to this project.
  • over 2 years ago: rsimai added keyword "neural" to this project.
  • over 2 years ago: rsimai added keyword "ai" to this project.
  • over 2 years ago: rsimai added keyword "artificial-intelligence" to this project.
  • over 2 years ago: rsimai originated this project.

  • Comments

    • jjanes
      over 2 years ago by jjanes | Reply

      I highly recommend the freely available course from FastAI for this group - https://www.fast.ai/

    • maritawerner
      over 2 years ago by maritawerner | Reply

      Interesting Link: https://en.wikipedia.org/wiki/Hallucination(artificialintelligence)

    Similar Projects

    Flaky Tests AI Finder for Uyuni and MLM Test Suites by oscar-barrios

    Description

    Our current Grafana dashboards provide a great overview of test suite health, including a panel for "Top failed tests." However, identifying which of these failures are due to legitimate bugs versus intermittent "flaky tests" is a manual, time-consuming process. These flaky tests erode trust in our test suites and slow down development.

    This project aims to build a simple but powerful Python script that automates flaky test detection. The script will directly query our Prometheus instance for the historical data of each failed test, using the jenkins_build_test_case_failure_age metric. It will then format this data and send it to the Gemini API with a carefully crafted prompt, asking it to identify which tests show a flaky pattern.

    The final output will be a clean JSON list of the most probable flaky tests, which can then be used to populate a new "Top Flaky Tests" panel in our existing Grafana test suite dashboard.

    Goals

    By the end of Hack Week, we aim to have a single, working Python script that:

    1. Connects to Prometheus and executes a query to fetch detailed test failure history.
    2. Processes the raw data into a format suitable for the Gemini API.
    3. Successfully calls the Gemini API with the data and a clear prompt.
    4. Parses the AI's response to extract a simple list of flaky tests.
    5. Saves the list to a JSON file that can be displayed in Grafana.
    6. New panel in our Dashboard listing the Flaky tests

    Resources