An engaging introduction to Machine Learning with Python
There are two options.
- Download all the notebooks from this repository and run them in Jupyter Notebook. Chapter one in eBook will get you started with that.
- Follow along using Google colab
Note: On each of those options, you'll find:
- A starter folder, which contains all the notebooks, that are empty in order to follow along.
- A final folder, which contains all the notebooks with all the source code.
- Download all Jupyter Notebooks from repo (zip-file-download).
- Unzip download (main.zip) appropriate place.
- Launch Ananconda and start JuPyter Notebook (Install it from here if needed)
- Open the first Notebook from download.
- Start watching the first video lesson (YouTube).
-
No installations needed.
-
Go to Colab Notebooks Folder
-
Start watching the first video lesson (YouTube).
-
Note: On each notebook, click on "Open in Colab", in order to open it on Google Colab
- Learn the advantages of ML
- Master a broad variety of ML techniques
- Solve problems with ML
- 15 projects with ML covering:
- k-Nearest-Neighbors Classifier
- Linear Classifier
- Support Vector Classification
- Linear Regression
- Reinforcement Learning
- Unsupervised Learning
- Neural Networks
- Deep Neural Networks (DNN)
- Convolutional Neural Networks (CNN)
- PyTorch classifier
- Recurrent Neural Networks (RNN)
- Natural Language Processing
- Text Categorization
- Information Retrieval
- Information Extraction
- The course puts you on an exciting journey with Machine Learning (ML) using Python.
- It will start you off with simple ML concepts to understand and build on top of that
- Taking you from simple classifier problems towards Deep Neural Networks and complex information extractions
- The course is structured in 15 sessions, where each session is composed of the following elements
- Lesson introducing new concepts and building on concepts from previous Lessons
- Project to try out the new concepts
- YouTube video explaining and demonstrating the concepts
- A walkthrough of concepts in Lesson with demonstrating coding examples
- An introduction of the Project
- A solution of the project
Worried about whether you have what it takes to complete this course?
- Do you have the necessary programming skills?
- Mathematics and statistics?
- Are you smart enough?
- Some basic knowledge of Python and/or programming is highly recommended.
- If you feel lost check out this free Python for beginners course
- It is structured in 17 lessons
- 8 hours of video tutorials
- 17 projects taking you from scratch
- It includes a free eBook with all concepts
- It has a GitHub repository with all examples and projects prepared for you
- If you feel lost check out this free Python for beginners course
- There will be links to help materials when using difficult programming concepts.
- Fortunately, when it comes to the complex math and statistics behind the Machine Learning models, you do not need to understand that part.
- All you need is to know how they work and can be used.
- It's like driving a car. You do not have to be a car mechanic to drive it - yes, it helps you understand the basic knowledge of an engine and what the engine does.
- Using Machine Learning models is like driving a car - you can get from A to B without being a car mechanic.
- A lot of people consider me a smart guy - well, the truth is, I'm not
- I just spend the hours learning it - I have no special talent
- In the end, it all depends on whether you are willing to spend the hours
- Yes, you can focus your efforts and succeed faster
- How?
- Well, structure it with focus and work on it consistently.
- Structure your learning - many people try to do it all at once and fail - stay focused on one thing and learn well.
- Yes, structure is the key to your success.
- I try to answer most questions. Feel free to contact me.