Vasileios Kochliaridis's Projects
In this repository, I will be hosting my personal webpage.
Advanced Machine Learning Algorithms including Cost-Sensitive Learning, Class Imbalances, Multi-Label Data, Multi-Instance Learning, Active Learning, Multi-Relational Data Mining, Interpretability in Python using Scikit-Learn.
An implementation of an Autonomous Vehicle Agent in CARLA simulator, using TF-Agents
Implementation of algorithms for big data using python, numpy, pandas.
Implementation of computer vision algorithms and image processing using Numpy & OpenCV
Implementation of fast Data Augmentation for Image Classification / Detection tasks.
Implementation of statistics algorithms for Machine Learning & Data Mining. The algorithms were implemented with the Scikit-Learn Library
Comparison of different Deep Reinforcement Learning (DRL) Frameworks. This repository includes "tf-agents", "RLlib" and will soon support "acme" as well.
Monitor Your Workout through a Webcam/IP Camera. No equipment is required, other than a camera and a laptop. This application could potentially replace a personal trainer, making it the idea app for workout.
Generation of Human-Like handwritten digits using different GAN Architectures. The models were developed using Low-Level Tensorflow.
This is a simple Team Chat written in Java.
This is my profile page.
Logo Detection of a custom small dataset. The dataset contains logos of 6 famous brands: Nike, Jordans, Adidas, Puma, Kappa, Quicksilver. The model was developed using the Object-Detection-API by Tensorflow
Prediction of Stock price using Recurrent Neural Network (RNN) models. Contains GRU, LSTM, Bidirection LSTM & LSTM combinations with GRU units. The models were deveoped using the keras module from Tensorlfow.
Noise-Adaptive Driving Assistance System (NADAS) using Deep Reinforcement Learning, State-Estimation & State Representation
Implementation of a Physics Informed Neural Network (PINN) written in Tensorflow v2, which is capable of solving Partial Differential Equations.
In this project, I analyze, plot and clean Tanzania's Water Pump Dataset, which is provided by DrivenData.org for a competition.
ProphitBet is a Machine Learning Soccer Bet prediction application. It analyzes the form of teams, computes match statistics and predicts the outcomes of a match using Advanced Machine Learning (ML) methods. The supported algorithms in this application are Neural Networks, Random Forests & Ensembl Models.
This project focuses on comparing different Reinforcement Learning Algorithms, including monte-carlo, q-learning, lambda q-learning epsilon-greedy variations, etc.
Construction of controllers for Shadow-Hand in Mujoco environment, using Deep Learning. 2 Different methods were used to create the controllers: a) Behavioral Cloning b) Deep Reinforcement Learning
Building High Performance Convolutional Neural Networks with TensorFlow
An implementation of an advanced movie search engine, using TMDB's data & Lucene's indexing. It is a desktop application, developed in Java
TraderNet-CRv2 - Combining Deep Reinforcement Learning with Technical Analysis and Trend Monitoring on Cryptocurrency Markets
Apply built-in state-of-the-art classifiers with the Keras library to Traffic Sign datasets
Clean Implementation of Unet3+ and validation on Cityscapes dataset.
This repository is the implementation of the paper: ViT2 - Pre-training Vision Transformers for Visual Times Series Forecasting. ViT2 is a framework designed to address generalization & transfer learning limitations of Time-Series-based forecasting models by encoding the time-series to images using GAF and a modified ViT architecture.
The purpose of this work is the modeling of the wine preferences by physicochemical properties. Such model is useful to support the oenologist wine tasting evaluations, improve and speed-up the wine production. A Neural Network was trained using Tensorflow, which was later tuned in order to achieve high-accuracy quality predictions.