Kyriakos Psallidas's Projects
Derivation of backpropagation equations based on specific activation functions & analysis of the behavior of activation function gradients across Neural Networks of varying depths
Probability theory fundamentals, polynomial regression from scratch and full Bayesian inference
Replication and extension of the single cell RNA-seq analysis paper "Single-cell RNA-seq enables comprehensive tumour and immune cell profiling in primary breast cancer"
Implementation using ONLY the Numpy library of classifiers and the evaluation of their performance on the iris plant and the pima Indians diabetes datasets.
The objective of this study is to cluster the countries using socio-economic and health factors that determine the overall development of the country and to characterize each resulting cluster (and, consequently, the countries it comprises) based on the relevant values of the above factors
Replication & from scratch implementation of the paper: Phoophakdee, B., & Zaki, M. J. (2007, June). Genome-scale disk-based suffix tree indexing. In Proceedings of the 2007 ACM SIGMOD international conference on Management of data (pp. 833-844).
My solutions to all exercises of the book Eloquent JavaScript 4th edition (2024)
Pipeline for binary classification algorithm evaluation with nested cross validation and Bayesian hyperparameter tuning with optuna, particularly suited for unbalanced medical datasets.
Qualitative and quantitative evaluation of the performance of clustering algorithms in HSI clustering
Image processing tasks in python using OpenCV
Profile README
This repository contains code to solve different tasks related to building, training and creating adversarial examples for classification models on the MNIST and CIFAR10 datasets.
Comparison of feature extraction and prediction of classical ML algorithms vs Deep Neural Networks for classifying patients into healthy or pneumonia-positive categories from chest X-ray images
This repository contains a generalized regression analysis problem solved from scratch, using only the Numpy library.
single-cell RNA seq Gaussian Mixture Model analysis pipeline. Accepts as input a single cell dataset (rows:cells x columns:gene expression) and provides their trajectories based on fitted Gaussian Mixture Models.
An application package for the collection, visualization and small scale analysis of catalogued data regarding single nucleotide polymorphisms across populations.
RNA folding dynamic programming, c-RMSD & d-RMSD analysis for protein similarity
Study on the performance of pre-trained models (VGG16, EfficientNetb0, ResNet50, ViT16) with weight fine tuning, as well as classical ML algorithms (Naive Bayes, Logistic Regression, Random Forest) on a dataset of 6.806 fungi microscopy Images utilizing Pytorch.