Update: big evolutions are planned, and I'm creating a Telegram group with contributors, if you want to join just e-mail me at [email protected]
Studying through the Internet means swimming in an infinite ocean of information.
Have you ever felt overwhelmed when trying to approach a new subject without a real “path” to follow? Were you hindered from obtaining deep knowledge and the ability to apply it?
Hi, I'm Giacomo.
I'm an Italian student currently having a stage in a shiny Machine Learning and AI startup in Bologna. My boss asked me if it was possible to create a study path for newcomers and myself, and I've contributed all my years of browsing around the internet for resources here. I have collected sources, projects, awesome tools, tutorial, links, best practices in the ML field, and organized them in an awesome and usable way.
This repository is intended to provide three complete and organic learning paths for the following fields:
-
Machine Learning
-
Business Intelligence (coming soon)
-
Cloud Computing (coming soon)
I have organized and collected in-depth guides about some Specializations and Tools. They are optional but highly recommended. You will need them to expand your skillset and expertise.
You will learn to understand and apply theory with hands-on projects.
By carefully following these guides, you will gain complete awareness and expendable skills from scratch.
You do not require any prior knowledge of machine learning, but be confident with programming and high school-level math to understand and implement most of the concepts.
Every source listed here is free or open source.
I tried to be concise to avoid information overhead.
I tried to organize the content hierarchically and by the level of complexity to give you a coherent idea of how things work.
Click on "watch", I'm updating this in the free time and on weekends.
If you want to contact me for whatever reason, just text me on Telegram @Clone95.
I think the second guide (Business Intelligence) will be out in 2 or 3 weeks. Yo!
- Latex
- GeoGebra
You can take them in order or choose the one that fits you the most, but I recommend you to walk through them all at least once.
I've planned two types of Specializations:
-
Data Specializations
- Data Preprocessing [Already Out!]
- Data Collection [Coming Soon - Next]
- Data Visualization [Coming Soon]
-
Soft Skills Specializations
- Effective Communication [Coming Soon]
- Impactful Presentations [Coming Soon]
- Pragmatic Decision Making [Coming Soon]
The former is about Data (you wouldn't have said that?) and is the core toolkit for everyone working with data. Working with data is an art form, and the rules of thumb and best practices will help you understand the way to deal with them. You need to develop a "sense" of what to do with the data, this "sense" is primarily driven by the situation and the experience. Because of that, these specializations will be strongly focused on exercises and practice.
The latter is about... everything that's not written in technical books. Use and master them, because they are the real value enabler for you. You can be the best developer or engineer in the world, but if you can't communicate your data to your audience, or use data to suggest practical action in the real world, you're useless for a company.
So, stay tuned because I'm building this section on weekends and free time, and I hope to provide you one specialization each week!
As usual, feel free to suggest improvements and collaborations :)
Everyone can commit their own guides, following the style I've chosen, and I'm proud to tell you that very soon the Tools Sections will host several guides about everything you need to know about a particular technology/language/methodology! I've already planned with some contributors a guide on Latex and one about ElasticSearch! So stay tuned!
You can already find here a cool Latex guide for beginners!
This is the roadmap of the coming guides (the Machine Learning one is already out).
