https://github.com/CllsPy/learn_ai

A repository chronicling my journey to understand AI, featuring experiments, projects, and lessons learned along the way
https://github.com/CllsPy/learn_ai

deep-learning huggingface kaggle-competition machine-learning nlp python pytorch

Last synced: 5 months ago
JSON representation

A repository chronicling my journey to understand AI, featuring experiments, projects, and lessons learned along the way

• Host: GitHub
• URL: https://github.com/CllsPy/learn_ai
• Owner: CllsPy
• Created: 2024-03-12T07:11:50.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2025-01-29T21:14:31.000Z (about 1 year ago)
• Last Synced: 2025-01-29T22:24:53.554Z (about 1 year ago)
• Topics: deep-learning, huggingface, kaggle-competition, machine-learning, nlp, python, pytorch
• Language: Jupyter Notebook
• Homepage:
• Size: 19.6 MB
• Stars: 1
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Roadmap de Estudos em Inteligência Artificial



Este repositório é um guia prático para você que deseja dominar os fundamentos de **Inteligência Artificial e Machine Learning**, inspirado no **Stanford AI Graduate Certificate** e organizado pela [Exaltitude](https://www.exaltitude.io/job-seekers#Roadmap).  

## O que você pode esperar

- O tempo médio de estudo varia de **1 a 2 anos** em dedicação parcial, mas o ritmo é totalmente ajustável.  

- O foco está em **entender profundamente os conceitos**, não em acelerar o processo.  

- Você terá contato com **matemática, programação, IA aplicada** e também dicas de **desenvolvimento de carreira**.  

## Estrutura do Roadmap

### Fase 1 – Fundamentos Matemáticos

- **Cálculo**: [Khan Academy](https://www.khanacademy.org/math/calculus-1), [Calculus for Dummies](https://amzn.to/4hF2xuH).  

- **Álgebra Linear**: [Khan Academy](https://www.khanacademy.org/math/linear-algebra), [Linear Algebra Done Right](https://linear.axler.net/).  

- **Probabilidade e Estatística**: [Stanford CS109](https://online.stanford.edu/courses/cs109-introduction-probability-computer-scientists), [Khan Academy](https://www.khanacademy.org/math/statistics-probability), [A First Course in Probability – Sheldon Ross](https://amzn.to/4f6Txxc).  

### Fase 2 – Fundamentos de Programação

- **Linux e linha de comando**: [Tutorial Ubuntu](https://ubuntu.com/tutorials/command-line-for-beginners#1-overview).  

- **Estruturas de Dados e Algoritmos**: [Google Tech Dev Guide](https://techdevguide.withgoogle.com/paths/data-structures-and-algorithms/), [Coursera Specialization](https://www.coursera.org/specializations/boulder-data-structures-algorithms).  

- **Python**: [Automate the Boring Stuff](https://automatetheboringstuff.com/), [Stanford Python](https://stanfordpython.com/#/), [NumPy Tutorial](https://youtu.be/XeixIlK7Tdg), [Pandas Docs](https://pandas.pydata.org/docs/getting_started/intro_tutorials/index.html).  

### Fase 3 – Fundamentos de IA

- **Machine Learning**: [Stanford CS229](https://online.stanford.edu/courses/cs229-machine-learning), [Andrew Ng ML Specialization](https://www.coursera.org/specializations/machine-learning-introduction), [Fast.ai](https://course18.fast.ai/ml.html).  

- **Artificial Intelligence (IA geral)**: [Stanford CS221](https://online.stanford.edu/courses/cs221-artificial-intelligence-principles-and-techniques), [MIT OCW](https://ocw.mit.edu/courses/6-034-artificial-intelligence-fall-2010/).  

### Fase 4 – Projeto de Conclusão (Capstone)

- Inspire-se em projetos do [ICML](https://icml.cc/Conferences/2020/Schedule) e [NeurIPS](https://neurips.cc/Conferences/2020/Schedule).  

- Utilize diretrizes como o [CS229 Final Report Guidelines](https://cs229.stanford.edu/final-report-guidelines.pdf).  

### Fase 5 – Eletivas Avançadas

- **Machine Learning com Grafos**: [CS224W](https://online.stanford.edu/courses/cs224w-machine-learning-graphs).  

- **Deep Learning**: [CS230](https://online.stanford.edu/courses/cs230-deep-learning).  

- **Visão Computacional**: [CS231N](https://online.stanford.edu/courses/cs231n-deep-learning-computer-vision).  

- **NLP**: [CS224N](https://online.stanford.edu/courses/cs224n-natural-language-processing-deep-learning).  

- **Robótica**: [CS223A](https://online.stanford.edu/courses/cs223a-introduction-robotics), [CS237A](https://online.stanford.edu/courses/cs237a-principles-robot-autonomy-i).  

- **Reinforcement Learning**: [CS234](https://online.stanford.edu/courses/cs234-reinforcement-learning), [CS224R](https://online.stanford.edu/courses/cs224r-deep-reinforcement-learning).  

- **Probabilistic Graphical Models**: [CS228](https://online.stanford.edu/courses/cs228-probabilistic-graphical-models-principles-and-techniques).  

## Desenvolvimento de Carreira

Aprender a programar é só metade do caminho. Para se destacar no mercado, você precisa também de preparação de carreira:  

- **Currículo**: [Ultimate Resume Handbook](https://www.exaltitude.io/resume-handbook?utm_source=roadmap), [Dicas no YouTube](https://youtu.be/kArOk8tudoM).  

- **Entrevistas**: [Cracking the Coding Interview](https://amzn.to/48a9X4z), [Blind 75 Leetcode](https://leetcode.com/discuss/interview-question/460599/Blind-75-LeetCode-Questions).  

- **Q&A ao vivo com Jean**: [LinkedIn Events](https://www.linkedin.com/events/jan-softwareengineeringcareersi7269411175199580160/comments/).  

- **Mercado de Trabalho**: [Tendências de Salários em Tech](https://youtu.be/_MT4SgfQ8QY), [Zero to AI ML Engineer](https://youtu.be/rZTiXIsFc6s).  

## Dicas de Estudo

- Defina horários fixos e seja consistente.  

- Faça pausas curtas para evitar sobrecarga.  

- Participe de comunidades online e troque experiências.  

- Construa pequenos projetos práticos.  

- Celebre seus avanços — cada etapa é um progresso real.  

## O que estou fazendo agora

Estou aplicando este roadmap de IA como meu guia pessoal de estudos, documentando aprendizados e referências neste repositório para que outros também possam aproveitar.

## Créditos e Inspiração

- [Exaltitude – AI Roadmap](https://www.exaltitude.io/job-seekers#Roadmap)  

- Documento de referência: *AI Roadmap based on Stanford AI Graduate Certificate*  

- Conteúdo e curadoria: **Jean K. Lee (Exaltitude)** – [YouTube](https://www.youtube.com/@exaltitude) | [LinkedIn](https://www.linkedin.com/in/jeanklee/)