- Table of Contents
- Introduction
- 🛠️ Tools and Technologies
- 🧠 Computer Vision Projects
- 🕹️ Reinforcement Learning Projects
- 📝 Natural Language Processing Projects
- License
- Contact
- Conclusion
This repository contains a collection of artificial intelligence projects that I have completed during my studies and research. The projects cover a variety of topics and techniques in the field of AI, including computer vision and reinforcement learning.
The following tools and technologies were used to develop the projects in this repository:
- Python
- Jupyter Notebook
- Paperspace (GET $10 FREE CREDIT: https://console.paperspace.com/signup?R=PWSZ8AL)
- Kaggle
- Hugging Face
- PyTorch
This project focuses on using machine learning algorithms to predict the likelihood of Alzheimer's disease in patients based on medical images of their brain. The model was trained on a dataset of brain images from both healthy individuals and patients with Alzheimer's disease, and achieved a high level of accuracy in predicting the disease.
In this project, I developed a machine learning model to predict the presence of pneumonia in medical images of the lungs. The model was trained on a dataset of chest X-rays from patients with and without pneumonia, and was able to accurately classify new images as either positive or negative for pneumonia.
This project explores the use of deep Q-learning to teach a computer program to play a simple game involving a taxi picking up and dropping off passengers in a grid-like environment. The model was trained using a deep neural network and was able to learn a policy that allowed it to navigate the environment and complete the game with high accuracy.
In this project, I developed a program that uses Q-learning to train a computer agent to play the same game as in the previous project. Q-learning is a simpler and more intuitive reinforcement learning technique than deep Q-learning, but requires more computation time to converge on an optimal policy. The resulting agent was able to complete the game with high accuracy after sufficient training.
This project explores the use of natural language processing to build a chatbot that can book train tickets. The chatbot is able to understand the user's intent and extract the relevant information from the user's input, and then use this information to book a train ticket.
This project explores the use of natural language processing to build a machine learning model that can classify tweets as either real or fake. The model was trained on a dataset downloaded in a kaggle competion here. The model score is as follows: 0.81765.
Distributed under the MIT License. See LICENSE.txt for more information.
Robin Marquet - @mrqt_robin - robin.marquet3@gmail.com
Project Link: https://github.com/rmarquet21/ai_research
Overall, this repository showcases a range of AI projects that demonstrate my skills and experience in computer vision and reinforcement learning. Each project is accompanied by detailed documentation and code, making it easy to replicate and build upon my work.