Language & Image Processing

This repository collects assignments, lecture material, and supporting resources for the Language & Image Processing course in the Master's program at CIMAT. The coursework blends Natural Language Processing (NLP) and Computer Vision (CV) with a focus on reproducible pipelines in Python.

📚 Course Content

This course covers key areas of natural language processing and computer vision including:

1. Introduction to NLP and traditional algorithms
2. Embeddings
3. Neural networks and text classification
4. Deep learning architectures for text
5. Transformers
6. Introduction to Computer Vision
7. Fundamentals of Convolutional Neural Networks (CNN)
8. Pre-trained models: VGG, ResNet
9. Diffusion models
10. Fine-tuning and feature extraction
11. Object detection with pre-trained models
12. Introduction to text in images
13. Text generation models in images

📁 Repository Structure

The repository follows the next structure:

language-image-processing/
├── nlp/                          # Natural Language Processing assignments
│   ├── 01_corpus_analysis/
│   └── 02_deep_learning_arquitectures/
├── cv/                           # Computer Vision assignments (upcoming)
├── LICENSE
└── README.md

📊 Assignments

Natural Language Processing (NLP)

Assignment	Module	Key Methods	Link
01	Corpus Analysis	Token statistics, Zipf law, TF-IDF, Logistic/SVM baselines	📂 View
02	Deep Learning Architectures	RNN/LSTM/GRU, LLaMA-3 LoRA, mDeBERTa, text generation & classification	📂 View

Computer Vision (CV)

Assignment	Module	Key Methods	Link
03	...	...	...
04	...	...	...

🛠 Technical Stack

Programming & Analysis:

• Python (≥3.10) for preprocessing, modeling, and experimentation
• Core libraries: pandas, numpy, scikit-learn, matplotlib, seaborn, spaCy, gensim, tqdm

Documentation & Reporting:

• LaTeX for formal reports
• Markdown for repository documentation
• Git for version control and collaboration

Development Tools:

• JupyterLab / VS Code for interactive exploration
• Virtual environments (venv) for isolated dependencies
• spaCy language models (es_core_news_sm) for Spanish NLP tasks

🚀 Getting Started

Prerequisites

• Python 3.10+
• pip and virtualenv (or python -m venv)
• Optional: GPU-enabled PyTorch/TensorFlow for advanced experiments
• LaTeX distribution for compiling reports

📄 License

This project is licensed under the MIT License — see LICENSE for details.

---

This repository represents academic work in natural language processing and computer vision.