Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/afondiel/intro-to-artificial-intelligence-free-course-le-wagon

Intro to Artificial Intelligence Free Course from @LeWagon
https://github.com/afondiel/intro-to-artificial-intelligence-free-course-le-wagon

ai ai-courses artificial-intelligence data-science lewagon machine-learning numpy pandas prophet-facebook regression-models scikit-learn sklearn

Last synced: 22 days ago
JSON representation

Intro to Artificial Intelligence Free Course from @LeWagon

Awesome Lists containing this project

README 

        
# Intro to Artificial Intelligence Free Course - Le Wagon



## Overview



Artificial Intelligence is an innovative and versatile field that enables machines to mimic human intelligence. 



It's applicable in numerous sectors like healthcare, finance, and entertainment, significantly impacting how we live and work.



## Course Contents



1. [Machine Learning Essentials](#)



Discover the fundamentals of Machine Learning, one of the most innovative and widely-used applications of Artificial Intelligence. Learn about what it really means, and optionally explore advanced topics such as K-Nearest Neighbors to build a robust foundation for your AI journey.



2. [Python & Scikit-learn 101](#)



Understand the significance of Python and Scikit-learn in AI programming. Learn how to set up and practice with Python and Jupyter to effectively manage your Machine Learning workflows.



3. [Predictive Modeling](#)



Dive into the world of predictive models in AI. Learn how to create predictions with Python, from salary forecasting to customer churn and even Apple stock predictions, enhancing the practicality and versatility of your AI applications.



4. [Real-World Applications](#)



Get hands-on experience with AI through a series of practical exercises. Learn how to apply Machine Learning concepts in real-life scenarios and solve tangible problems, bolstered by supportive resources like cheat sheets and further learning suggestions.



## Tools & frameworks



- [Pandas](https://pandas.pydata.org/)

- [Numpy](https://numpy.org/)

- [Scikit-learn](https://scikit-learn.org/stable/)

- [Prophet (Facebook)](https://facebook.github.io/prophet/docs/quick_start.html)



## Notebooks



All notebooks are available in [/lab](./lab/) repository. 



## What from here? 



If you want to go further and do not know what course to take next, this great [blog post](https://blog.lewagon.com/skills/how-to-learn-artificial-intelligence-from-scratch/) from @lewagon might answer all your question, just as it did mines.  



## References



- [Course link - Le Wagon](https://start.lewagon.com/courses/intro-to-artificial-intelligence)



Dataset



- Stock Predictions: [IEX Cloud](https://iexcloud.io/docs/api/)

- Stock data can also be collected by scraping finance web sites (ex: [finance.yahoo.com](https://finance.yahoo.com/quote/AAPL/?p=AAPL) ) using Python API package such as [Beautiful Soup.](https://en.wikipedia.org/wiki/Beautiful_Soup_(HTML_parser))

  - Here's an hands-on [notebook](https://github.com/afondiel/research-notes/blob/9fa1cffe8459a7a61d54afddffb230d1df63d2a4/datascience-notes/job/data-engineering-notes/WebScraping_Review_Lab.ipynb#L197) with Beautiful Soup & Pandas DataFrame



Tools



- setosa.io (blog)

- ml-playground.com (model playground) 



Virtual environment:



- https://mybinder.org/ 

- https://datalore.jetbrains.com/



ML API:



- Facebook Prophet: https://facebook.github.io/prophet/docs/quick_start.html



Papers:



- [Explainable-Artificial-Intelligence-a-Systematic-Review-XAI-paper-2020](./docs/Explainable-Artificial-Intelligence-a-Systematic-Review-XAI-paper-2020.pdf)