Dimitrios Reppas's repositories
Analysis-and-prediction-of-stock-prices
The main objective of this project is the analysis and prediction of stock prices. As far as it concerns the predictions, a variety of classic machine learning algorithms and deep neural networks are used for: One-step price forecast, Long-term price forecast and Prediction of stock price movements.
On_visual_explanation_of_supervised_and_self-supervised_learning
Visualization methods to interpret CNNs and Vision Transformers, trained in a supervised or self-supervised way. The methods are based on CAM or on the attention mechanism of Transformers. The results are evaluated qualitatively and quantitatively.
A-notebook-for-complete-Exploratory-Data-Analysis-with-SQL
In this project, a Jupyter Notebook was developed suitable for exploratory data analysis and formulation of SQL queries. This web-based environment is perfect for interactive data analysis, visualizations and can be associated with database management systems.
Detect-pneumonia-in-chest-X-ray-images
The main objective of this project is to develop an intelligent system to detect pneumonia in chest X-ray images. In addition to developing detection algorithms, data exploration, analysis, and preprocessing are also performed.
End-to-end-wine_quality_prediction
This repo contains an end-to-end project for predicting wine quality using machine learning.
House_price_analysis_and_prediction
The main objectives of the project are: exploratory data analysis, pre-processing, feature extraction, price prediction of houses.
MIM_on_self-supervision
In this project new masking strategies are proposed for more competitive MIM-based self-supervised learning. Furthermore, a new loss function, based on contrastive learning, is introduced and achieves improvements over the baseline when used with different masking strategies.
semantic-segmentation_of_aerial_images
The primary objective of the project is to to develop an intelligent system that segments aerial images. In addition, exploratory data analysis, preprocessing of data, and thorough evaluation of experimental results are a few of the steps performed.