Skip to content
View mlojek's full-sized avatar

Highlights

  • Pro

Block or report mlojek

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
mlojek/README.md

Machine Learning engineer dedicated to writing high quality code that speaks for itself.

About me

🔬 President of AI Science Society "Golem"
💼 ML engineer and researcher @ AI division of WUT
🎓 Graduated as BEng in CS and ML @ WUT
🎓 ML MEng student @ WUT

Skills

  • languages: Python C++
  • machine learning: pytorch scikit-learn langchain wandb.ai
  • multi-agent systems: crewai
  • data science: numpy pandas
  • devops: docker CI/CD unit testing airflow
  • hobby: arduino

Featured projects

machine learning python CI/CD docker

Optilab is a Python framework designed to streamline the prototyping and benchmarking of black-box optimization algorithms. It offers a comprehensive suite of tools for comparative analysis and results reporting, including statistical tests and visualizations like ECDF and convergence plots. Optilab is readily accessible via PyPI and Docker Hub, with comprehensive documentation hosted on Read the Docs. The project utilizes continuous deployment pipelines to ensure timely delivery of new versions upon each release.

pytorch machine learning wandb.ai python

This project investigated the application of the CMA-ES metaheuristic for training neural networks. While deep learning traditionally relies on gradient-based optimization methods like SGD and Adam, CMA-ES represents a state-of-the-art black-box optimization algorithm known for its efficiency and performance. This research compared the performance of CMA-ES against traditional gradient-based approaches in the context of training neural networks, analyzing the results to evaluate the potential of CMA-ES in this domain.

machine learning langchain llm python

Codemate is a command-line interface (CLI) coding assistant designed to alleviate mundane and repetitive tasks in software development. Leveraging large language models (LLMs) such as those powering ChatGPT and GitHub Copilot, Codemate provides developers with tools to efficiently document code, clarify complex sections of source code, and generate new code based on specific requirements.

Other projects

machine learning python tensorflow

Computer Vision program that matches image with the most similar YuGiOh! card.

C++ unit tests

C++ library for non-linear dialogues in roleplaying games.

arduino C++

Arduino device to navigate the computer with hand gestures.

mutli-agent systems crewai llm python

A multi-agent LLM system to kickstart a new software development project.

Pinned Loading

  1. optilab optilab Public

    Python framework for black-box optimization.

    Python 1

  2. codemate codemate Public

    LLM-powered CLI tool to help software developers

    Python 1

  3. cma_neuroevolution cma_neuroevolution Public

    Using CMA-ES to optimize neural networks

    Python 1

  4. which-yugioh-card-are-you which-yugioh-card-are-you Public

    Using the power of machine learning to find out which Yu-Gi-Oh! card you look like

    Python 1

  5. rpg_dialogues rpg_dialogues Public

    C++ library for non-linear dialogues

    C++ 1

  6. wse-stock-analysis wse-stock-analysis Public

    Using statistics to prove a stock trading strategy

    R 1