Image-processing software for cryo-electron microscopy

House price prediction

Mithilfe von Machine Learning und Open Data zu Unfällen in Berlin (2018-2021) beantworten wir folgende Frage: Was sind die wichtigen Faktoren/Einflüsse auf Unfallgefahr? Und wie gut lässt sich damit die Unfallschwere überhaupt vorhersagen?

TOmographic MOdel-BAsed Reconstruction (ToMoBAR) software

This is an expansion of dsb318-group4 (see repo: dsb318-group4), in which we collaborated to predict high school graduation rates in CA from other trends (e.g., poverty rate, availability of e-cigarettes). Collaboration between Eli and Emily.

This repository contains various implementations of machine learning algorithms and methods for solving different types of problems, ranging from classification to regression.

The set of CPU/GPU optimised regularisation modules for iterative image reconstruction and other image processing tasks

“Disparitybased space-variant image deblurring,” Signal Processing: Image Communication, vol. 28, no. 7, pp. 792–808, 2013.

Techniques for Regularization of Inverse Problems in Python (TRIPs-Py).

HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering (CVPR'23)

Regularization is a crucial technique in machine learning that helps to prevent overfitting. Overfitting occurs when a model becomes too complex and learns the training data so well that it fails to generalize to new, unseen data.

This repository shows a use case of Graph ML for casinos in marketing: Market Segmentation . Skills: Azure SDK, azure datalake, node2vec, graphml, geometric pytorch, gnn

Numerical methods for estimating the Bregman distance decay rate using cylindrical shearlet regularization for dynamic tomography

This repository contains a Python implementation of a neural network from scratch. Final project for the "Machine Learning 23/24" course.

This repository provides the implementation of the Group-Sparse Subspace Clustering (SSC) method with the innovative Elastic Stars (ES) regularization.

Implementation of Averaged Stochastic Gradient Descent for PyTorch. Two versions: 1. ASGD with fixed triggering point, 2. Non-monotonically triggered ASGD.

Implementation of SvF-technology of balanced identification of mathematical models by experimental data

Second practical assignment for the course "I302 - ML and Deep Learning". The work consists of three regression problems where different models are designed from scratch.

Bachelor's Thesis of Mathematics and Computer Science in UGR.