Deep Convolutional Encoder-Decoder Architecture implemented along with max-pooling indices for pixel-wise semantic segmentation using CamVid dataset.

Built an algorithm to identify canine breed given an image of a dog. If given image of a human, the algorithm identifies a resembling dog breed.

Keras implementation of influential CNN architectures.

Build a Deep Convolutional Generative Adversarial Networks (DCGANs) to generate new images of faces.

Deep Convolutional Encoder-Decoder Architecture implemented along with max-pooling indices for pixel-wise semantic segmentation using CamVid dataset.

Handwriting Recognition with Deep Convolutional Neural Network (DCNN)

Face Detection and Recognition using One Shot Learning

Built an algorithm to identify canine breed given an image of a dog. If given image of a human, the algorithm identifies a resembling dog breed.

Labeling Tool Kit and Neural Network for Autonomous Lawnmower

Implementation of DCGAN on the Street View House Numbers (SVHN) dataset.

Deep Convolutional Neural Network for CIFAR10 problem. Achieved 91.49% accuracy.

Breast cancer detection on BreakHis dataset

Detecting of COVID-19 induced Pneumonia in Chest X-ray Images using using Modified XceptionNet

Cilia are micro-scopic hairlike structures that protrude from literally every cell in your body. They beat in regular, rhythmic patterns to perform myriad tasks, from moving nutrients in to moving irritants out to amplifying cell-cell signaling pathways to generating calcium fluid flow in early cell differentiation. Cilia, and their beating patt…

Deep CNN to classify pneumonia patients through x-ray images using PyTorch

My solutions to the assignments in Introduction to Machine Learning course at Tel Aviv University (course number: 0368-3235)

Bangla Handwritten Character Recognition System Using a Deep Convolutional Neural Network

Code for our paper "Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism", by I. Gkartzonika, N. Gkalelis, V. Mezaris, presented and included in the Proceedings of the ECCV 2022 Workshop on Vision with Biased or Scarce Data (VBSD), Oct. 2022.

This project uses machine learning techniques to classify songs into different music genres. It analyzes various audio features and metrics to identify the genre of each song accurately.