Python 3.10+
Main environment for notebooks, scripts, and scientific library integration.
AI lab
AI_studies
A repository dedicated to consolidating AI studies and prototypes, exploring machine learning, deep learning, NLP, computer vision, and generative models.
- Purpose
- Document continuous AI learning and keep a living archive of notebooks, datasets, and utility scripts.
- Status
- Open to experiments, contributions, and community-led evolution.
Overview
Explore, test, and document artificial intelligence
AI_studies works as a central lab for experiments. Each learning cycle is documented for reuse and sharing with other developers.
- Curated notebooks that demonstrate AI techniques on real-world problems.
- Versioned datasets to ensure reproducibility and future comparisons.
- Utility scripts that automate training, evaluation, and visualisation pipelines.
- Transparent roadmap with topics like generative models, time series, and intelligent recommendations.
Technical stack
Modern tools for rapid experimentation
The base combines the Python ecosystem with established frameworks for machine learning, visualisation, and data processing.
AI frameworks
PyTorch, TensorFlow, Hugging Face Transformers, and Scikit-learn for supervised and generative training.
Data & visualisation
Pandas, NumPy, and Matplotlib for efficient data manipulation and analytics dashboards.
Architecture
Structure designed to scale without losing order
Each experiment lives in its own folder, making replication, comparisons, and future publishing easier.
AI_studies/
├── notebooks/ # Jupyter experiments
├── datasets/ # Datasets used
├── models/ # Trained models and checkpoints
├── scripts/ # Utilities and pipelines
└── README.md # Central documentation
Installation
Start your tests with a few commands
The repository is lightweight and can be used locally, in Google Colab, or in cloud environments.
- Clone the repository and enter the folder:
git clone https://github.com/eduardo45MP/AI_studies.git
cd AI_studies- Create and activate a Python virtual environment:
python3 -m venv venv
source venv/bin/activate # Linux/macOS
# .\venv\Scripts\activate # Windows- Install the dependencies needed for each notebook or script:
pip install -r requirements.txt # when available
# or install individual libraries per experiment
Use Google Colab for quick tests by sharing notebooks directly from the notebooks/ folder.
Open Source
How to contribute to AI_studies
The project values collaborative contributions that document experiments, improve datasets, or propose new challenges.
New experiments
Bring well-documented notebooks with insights and model comparisons.
Curated datasets
Include public or synthetic datasets with a README covering license, format, and usage.
Utility scripts
Automate training, evaluation, or deployment flows and share best practices.
Open an issue with the contribution scope before the PR for quick alignment. Also review the documents in portfolio/docs/ to keep the visual and narrative pattern aligned.