Magnus's Projects
Project from Novo Nordisk's AgarVision hackathon, utilizing DenseNet-121 & YOLOv8 for agar plate analysis and colony counting.
Predicting Customer Product Preference
10 Weeks, 20 Lessons, Data Science for All!
This project analyzes employee data from the Employees Sample Database, using SQL and Tableau.
Exam project in foundations of data science. It includes three main components: Sub-Numpy, a Python library mimicking Numpy functionalities; Hamming's Code, focusing on error detection and correction in data transmission; and Text Document Similarity, which explores various algorithms to assess textual similarities.
Huginn Hears is a local app that transcribes and summarizes your meetings in Norwegian and English, using state-of-the-art models and open-source libraries. No cloud needed, run everything offline.
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
LLM inference in C/C++
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
Config files for my GitHub profile.
The project extracts movie data using TheMovieDB API, processes it using TF-IDF and cosine similarity for generating recommendations, and stores the data in a DuckDB database. The system is encapsulated within a FastAPI web application and can be deployed using Docker. It provides movie recommendations in JSON format.
Trained machine learning models to forecast used boat listing views, enabling a marketplace to optimize inventory by identifying low traction listings. Key techniques included data preprocessing, feature engineering, model evaluation, and hyperparameter tuning.
Advanced tumor segmentation using Attention U-Net on MIP-PET images for DM i AI 2023.