[🇧🇷 Português] [🇺🇸 English]

1- 🧠 Machine Learning / Main Repository

PUC-SP • 5th Semester • 2026
Neural Networks • Deep Learning • Real-world Applications

Machine Learning Integrated Project - PUC-SP 5th Semester (2026)

Institution: Pontifical Catholic University of São Paulo (PUC-SP Humanistic AI & Data Science • 5º Semestre • 2026
School: Faculty of Interdisciplinary Studies
Course Repo: INTEGRATED PROJECT: MACHINE LEARNING - 72 Hours
Professor: ✨ Rooney Ribeiro Albuquerque Coelho
Extensionist Activities: Social projects with open-source software for community support.

Note

⚠️ Heads Up

• Projects may be made publicly available whenever possible
• Focus on hands-on experience with real datasets
• Activities follow PUC-SP academic and ethical guidelines
• Restricted content remains confidential

Tip

🚀 AI Resources

High-signal links for learning, building, and understanding modern AI systems.

📘 Core Reading

• Hands-On Machine Learning with Scikit-Learn & TensorFlow — Aurélien Géron

🔗 References

• Stanford Online — AI Programs
• Building LLMs — Yann Dubois (Stanford / Alpaca)
• CS229: Machine Learning — Stanford
• LLMs Intro — Andrej Karpathy
• Karpathy Blog
• Software Is Changing (Again)
• AI Inference vs Training — Cloudflare
• RNNs Effectiveness
• run.c (llama2.c)

_Signal > noise._

building-llms-yann-dubois-stanford-cs229-2024.mp4

Reference
Dubois, Y. (2024). Introduction to Building Large Language Models [Video].
Stanford University — CS229 Machine Learning.
Available at: Watch on YouTube

Course Roadmap — Neural Networks

This repository outlines a structured journey from foundations to advanced neural architectures, combining theory, hands-on practice, and real-world applications.

Phase I — MLP → fundamentals, training, evaluation
Phase II — Deep Learning → CNNs, RNNs, GANs, Reinforcement Learning

foundations → modeling → training → applications

What is Machine Learning?

Imagine teaching a robot puppy to fetch a ball. You show it many examples (data), it tries, makes mistakes, and improves over time without explicit instructions.

That’s Machine Learning: systems that learn patterns from data.

Table of Contents

• Course Roadmap — Neural Networks
• What is Machine Learning?
• Architecture Applications
• Neural Networks Course Roadmap
• Folder Structure
• Related Project Repositories
• How to Use This Repo
• Grading & Assessment
• Learning Resources
• Tooling Stack
• Contributing Guidelines
• Bibliographic References
• Contact Me

Architecture Applications - Core Learning Pillars

Acronym	Full Name	Primary Application	Real-World Use
CNN	Convolutional Neural Network	Computer Vision	Image classification Object detection Facial recognition
MLP	Multilayer Perceptron	Classic Neural Networks	Tabular prediction Regression Binary classification
RNN	Recurrent Neural Network	Sequential Data	Text generation Time series forecasting Speech recognition
GAN	Generative Adversarial Network	Data Generation	Image synthesis Data augmentation Creative AI

Neural Networks Course Roadmap

Tip

• Part I → fundamentos e MLP
• Part II → visão computacional e modelos avançados
• Progressão: teoria → prática → aplicações

Week	Topic Summary	Notes/Files
	🧠 Part I — MLP (Foundations)
1	Intro to Machine Learning	/week-1/intro-ml.ipynb
2	Perceptron & basics of Neural Networks (MLP)	/week-2/perceptron/
3	Training fundamentals: Loss & Hyperparameters	/week-3/training/
4	Building MLPs with TensorFlow & PyTorch	/week-4/tf-pytorch/
5	Evaluating MLPs: Metrics & data handling	/week-5/evaluation/
6	Data preprocessing & feature engineering	/week-6/preprocessing/
7	Advanced MLPs & preprocessing (PyTorch/TensorFlow)	/week-8/advanced-nns/
8	Advanced MLPs, preprocessing, TensorBoard (PyTorch/TensorFlow)	/week-8/advanced-nns/
------	-------------------------------------------------------------------------------	--------------------------------------
	🖼️ Part II — CNNs & Advanced Architectures
9	Seminar 1	/seminar-1/
10	CNNs: Convolutions, pooling & architectures	/week-10/cnn-intro/
11	Training CNNs: optimization & regularization	/week-11/cnn-training/
12	CNN Applications (vision tasks & augmentation)	/week-12/cnn-apps/
13	RNNs (LSTM/GRU) — sequence modeling	/week-13/rnns/
14	Encoder–Decoder (translation & generation)	/week-14/encoder-decoder/
15	GANs — generative models	/week-15/gans/
16	Holiday (Corpus Christi) — No class	—
17	Reinforcement Learning (Q-Learning, SARSA)	/week-17/rl/
18	Seminar 2	/seminar-2/

Folder Structure

graph TD
    A[📁 Root Repository] --> B[computer-vision]
    A --> C[classic-nn]
    A --> D[sequential-data]
    A --> E[data-generation]
    A --> F[projects]
    A --> G[notebooks]

  style A fill:#0f172a,stroke:#1abc9c,color:#ffffff

Loading

Related Project Repositories

Project	Architecture	Status
Image Classifier	CNN	Coming Soon
Time Series	RNN	Coming Soon
Image Generator	GAN	Coming Soon

How to Use This Repo

1. Clone: git clone https://github.com/yourusername/PUC-SP-ML-Integrated-Project-2026.git.
2. Add weekly folders with README.md, .ipynb, .py files.
3. For PyTorch (local/Apple M): pip install torch. Fast on M-chips!
4. TensorFlow: pip install tensorflow.
5. Run notebooks in Colab or Jupyter. Share publicly for extensionist credit.

Grading & Assessment

- Seminar 1 (16 Apr 2026): Individual, weight 0.5.
- Seminar 2 (18 Jun 2026): Individual, weight 0.5.

Methods: Dialogued lectures, TF / PyTorch projects, active methodologies, continuous evals.

Learning Resources

- PyTorch Tutorials
- Fast.ai Practical Deep Learning
- Papers With Code

⚡️ Getting Started

git clone https://github.com/yourusername/project.git
pip install torch torchvision tensorflow pandas numpy matplotlib wandb

Evaluation

Component	Weight
Labs	20%
Projects	40%
Presentations	20%
Exam	20%

Tooling Stack

pip install torch torchvision tensorflow pandas numpy matplotlib wandb

Contributing Guidelines

1. Fork → Clone → Branch (feat/cnn-week3)
2. Add notebooks to architecture folders
3. Update weekly schedule table
4. Submit PR with results

Bibliographic References

* Core Literature:

- Goodfellow et al. Deep Learning (2016) — Foundational architectures
- LeCun et al. LeNet CNN (1998) — Computer Vision
- Hochreiter & Schmidhuber. LSTM (1997) — Sequential Data
- Goodfellow et al. GANs (2014) — Data Generation

* Basic

- GÉRON, Aurélien. Hands-On Machine Learning with Scikit-Learn & TensorFlow. O’Reilly Media, 2019.
- NETTO, A.; MACIEL, F. Python for Data Science and Machine Learning Made Simple. Alta Books, 2021.
- SILVA, F. M. da et al. Artificial Intelligence: Applications in Various Human Activities. Sagah, 2019.
- WITTEN, I. H. et al. Artificial Intelligence: A Machine Learning Approach. LTC, 2021.

* Complementary

- BIFET, A. et al. Machine Learning for Data Streams. MIT Press, 2018.
- CANO, A. Social Media and Machine Learning. IntechOpen, 2020.
- HUTTER, F.; KOTTHOFF, L.; VANSCHOREN, J. Automated Machine Learning: Methods, Systems, Challenges. Springer Nature, 2019.
- SUD, K. et al. Introduction to Data Science and Machine Learning. IntechOpen, 2020.
- THOMAS, C. Data Mining. IntechOpen, 2018.

💌 Let the data flow... Ping Me !

🛸๋ My Contacts Hub

────────────── ⊹🔭๋ ──────────────

➣➢➤ Back to Top

Copyright 2026 Mindful-AI-Assistants. Code released under the MIT license.