AI Foundation and Learning Models

Open courseware on AI fundamentals and learning models — from supervised and unsupervised ML to Deep Learning and Generative AI.

---

What you'll learn

• Frame AI problems and select the right learning paradigm
• Build and evaluate supervised classifiers with proper metrics
• Detect fraud and cluster data with unsupervised methods
• Forecast time series with classical and neural approaches
• Train CNNs, RNNs, LSTMs and Autoencoders from scratch
• Implement gradient descent and understand backpropagation
• Generate images with GANs and Stable Diffusion
• Apply Attention mechanisms and the Transformer architecture
• Orchestrate LLM workflows with LangChain
• Run real-time object detection with YOLO

Prerequisites

Topic	Level
Python	Basic
Pandas & NumPy	Basic
Statistics fundamentals	Basic

---

Contents

Notebooks are in Notebooks/, datasets in Datasets/, and lecture slides in Slides/.

#	Notebook	Topics
01	Demo1_URL_Classifier.ipynb	Supervised learning, URL classification, text features
02	Demo2_Comparacao_Metricas.ipynb	Accuracy, F1, AUC, confusion matrix
03	Demo2_5_Time_Series_Call_Center_Forecast.ipynb	Time series, forecasting, call center demand
04	Demo3_Fraud_Detection.ipynb	Fraud detection, imbalanced data, payment transactions
05	Demo4_Kmeans_Crime_data.ipynb	K-Means clustering, crime data
06	Demo4_5_Descida_Gradiente.ipynb	Gradient descent from scratch, backpropagation
07	Demo5_Autoencoders.ipynb	Autoencoders, latent space, dimensionality reduction
08	Demo6_CNN_CIFAR10.ipynb	Convolutional Neural Networks, CIFAR-10 image classification
09	Demo7_RNN_SpamFilter.ipynb	Recurrent Neural Networks, spam classification
10	Demo8_LSTM_IMDB.ipynb	LSTMs, sentiment analysis, IMDB dataset
11	Demo9_GANs_CIFAR10.ipynb	Generative Adversarial Networks, image generation
12	Demo10_Atencao_Transformers.ipynb	Attention mechanisms, Transformer architecture
13	Demo11_Opt_Stable_Diffusion.ipynb	Stable Diffusion, text-to-image generation
14	Demo12_LangChain_Didatico.ipynb	LangChain, LLM orchestration, chains and agents
15	Demo_YOLO_Recognition.ipynb	YOLO, real-time object detection, computer vision

---

Getting Started

Option 1 — Google Colab (recommended)

Open any notebook directly on GitHub and click Open in Colab at the top of the file.

Option 2 — Google Drive

Slides and full course materials are available at drive.google.com.

Option 3 — Local

git clone https://github.com/ahirtonlopes/AI-Foundation-and-Learning-Models.git
cd AI-Foundation-and-Learning-Models
python -m venv .venv && source .venv/bin/activate
pip install scikit-learn pandas numpy matplotlib tensorflow keras langchain diffusers jupyter
jupyter notebook

---

Suggested Learning Path

Foundations → Demos 01 → 02 → 03 → 04 → 05
Deep Learning → Demos 06 → 07 → 08 → 09 → 10
Generative AI → Demos 11 → 12 → 13 → 14 → 15

---

Author

Prof. Dr. Ahirton Lopes · LinkedIn · Google Scholar

Contributions are welcome — open an issue or submit a pull request.

License

MIT