Skip to content
View cotenthusiast's full-sized avatar

Block or report cotenthusiast

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
cotenthusiast/README.md

Hi, I'm Karl 👋 Software Engineering student at Queen's University Belfast, focused on ML research and building from first principles. Current focus

Conducting reproducible LLM evaluation research with clean experiment pipelines Implementing core ML models from scratch to build deep understanding Exploring benchmark reliability and robustness in language models

Featured

Mitigating MCQ Selection Bias in LLMs via Two-Stage Prompting https://github.com/cotenthusiast/two-stage-prompting-research Multilayer Perceptron From Scratch (NumPy, Fashion-MNIST) https://github.com/cotenthusiast/neural-network-from-scratch Logistic Regression From Scratch https://github.com/cotenthusiast/logistic-regression-from-scratch

Tech Python, NumPy, Pandas, Matplotlib, PyTorch, Git, LaTeX

Pinned Loading

  1. two-stage-prompting-research two-stage-prompting-research Public

    Research code for studying whether two-stage prompting and MCQ debiasing methods reduce positional bias across MMLU and ARC-Challenge.

    Python

  2. neural-network-from-scratch neural-network-from-scratch Public

    Neural network from scratch in NumPy with a clean src/ layout, unit tests, and runnable train/eval scripts that save reproducible artifacts (loss curves, configs, metrics).

    Python

  3. logistic-regression-from-scratch logistic-regression-from-scratch Public

    Quant-style classification engine benchmarked on the sklearn breast cancer dataset. Logistic regression built from scratch in NumPy (sigmoid, L2 log-loss, gradients, mini-batch GD), with reproducib…

    Python

  4. linear-polynomial-from-scratch linear-polynomial-from-scratch Public

    From-scratch 1D linear regression trained with gradient descent (MSE). Includes feature scaling for stability, parameter conversion back to original units, and plots for loss vs epochs and fitted l…

    Python