mhabibi's Projects
A machine learning solution for automating nucleus detection in biomedical images, leveraging the U-Net architecture to accelerate medical research and disease treatment discovery.
A data-driven project to predict the success of Falcon 9 rocket landings, crucial for cost analysis and competitive strategy in the space industry. Involves data manipulation in Pandas, JSON data processing, and insightful analysis using Python.
Enhanced CNN model for malaria cell classification, featuring Class Activation Mapping (CAM) as a non-agnstic technique for anomaly localization and LIME (Local Interpretable-agnostic Explanation) for interpretability, ensuring high accuracy and transparent AI diagnostics.
Python code accompanying the course "A deep understanding of deep learning (with Python intro)"
Exploring the depths of generative learning with a $\beta$-Variational Autoencoder ($\beta$-VAE) applied to the MNIST dataset for robust digit reconstruction and latent space analysis.
Projektausarbeitung zum Wahlmodul - Sondergebiete der Simulation - WS21/22
LIME for TimeSeries enhances AI transparency by providing LIME-based interpretability tools for time series models. It offers insights into model predictions, fostering trust and understanding in complex AI systems.
Code for "Machine Learning for Physicists 2020" lecture series
Minimal and clean examples of machine learning algorithms implementations
Exploring advanced autoencoder architectures for efficient data compression on EMNIST dataset, focusing on high-fidelity image reconstruction with minimal information loss. This project tests various encoder-decoder configurations to optimize performance metrics like MSE, SSIM, and PSNR, aiming to achieve near-lossless data compression.
Welcome to the Physics-based Deep Learning Book (v0.2)
The open-source particle-in-cell post-processor.
Deep Convolutional Neural Networks and Machine Learning Models for Analyzing Stellar and Exoplanetary Telescope Spectra
Various VAEs