Skip to content
View kgourgou's full-sized avatar
🪢
Back to tinkering
🪢
Back to tinkering
101 followers · 279 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Organizations

@gridclub

Block or report kgourgou

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kgourgou/README.md

Hi there 👋

I work as an ML researcher, currently interested in Bayesian modelling, language models, causal inference, and using ideas from information theory on the above.

I'm also slowly working through the basics of category theory as well as persistent homology. I'd love to understand how ideas from cat. theory map to applied questions, e.g., the work of Fong, Spivak, et al., with Bayesian networks and data manipulations. For persistent homology, I want to see how tools can be used to learn more about how language models tick.

Pinned Loading

  1. setfit-integrated-gradients setfit-integrated-gradients Public

    Hacking SetFit so that it works with integrated gradients.

    Python 2 2

  2. Linear-Perceptron Linear-Perceptron Public

    An IPython notebook with an implementation of the linear perceptron algorithm.

    Jupyter Notebook 3 4

  3. machine-learning-zettelkasten machine-learning-zettelkasten Public

    Insert backlinks to markdown documents by using sklearn and cosine similarity.

    Python 7

  4. adaptive-importance-sampling-BN adaptive-importance-sampling-BN Public

    Experimental code: adaptive importance sampling for bayesian networks.

    Python 8 2

  5. raggler raggler Public

    Simple, local-first, retrieval-augmented generation without tears (or API keys). Powered by MLX and AlphaMonarch.

    Python 1