Applied Machine Learning without coding using Orange 3
What you'll learn
- Learn the basics of machine learning without any coding!
- Will use Orange 3 to learn about a variety of problems and ways you can solve them using the tools provided in the software.
- By the end of the course you will have a solid understanding of the most used machine learning algorithms for regression, forecasting and classification and how to prototype solutions in Orange 3
- There is no requirement for knowing Python or R for this course. Some basic statistics knowledge is required.
- Would also be helpful if you watch some introductory videos about Orange 3 on YouTube
This is a course about data science and machine learning without using any programming!
Orange 3 is used as the platform for the course. It is public domain and very powerful tool with a lot of flexibility. It is a visual environment making it very easy to demonstrate your work to others. You do not need to have any background in machine learning in order to follow this course. I have tried to keep the concepts very simple and provide enough theory to get you started. I provide resources for further reading if you want to advance your knowledge in machine learning and data science.
Although Orange 3 is a simple tool, it can accomplish advanced tasks. I did not cover all of Orange 3's capabilities, however at the end of the course you will be able to experiment with all of its features.
I will cover a variety of topics:
Handling of imbalanced data sets
Modelling for both classification and regression problems
Support vector machines
Time series forecasting. This is normally a subject of advanced courses but I thought to include it and give you an idea of how it is performed, as so many real life problems are time series
Image classification. It is really fast and fun with Orange 3 and very easy to understand and expand it as required
I am also showing how to use Python coding and mix it with the Orange user interface to perform variable transformation, but that is only the beginning. Once you become familiar, you will realize that it is a very powerful option to have in your hands!
Hope you have a productive learning experience with this course!
Who this course is for:
- Students starting their journey on statistics and machine learning.
- Researchers that want to have control over their data analysis without having to use a statistician and without having to learn to code in Python or R.
- Industry practitioners who want to use a tool that is more powerful than Excel and other spreadsheet based tools, but don't want to spend too much time learning a new tool.
- Experienced statisticians that want to use a simple visual way to explain to others how the algorithms work
I finished my Ph.D. in Chemical Engineering, specializing in advanced control systems way back in 1995. At that time MATLAB was starting to become the tool of choice for academics, Mosaic was our favourite browser and computers were very slow.
I was lucky enough to have access to a main-frame at that time and started to perform programming in C++ for my thesis. I remember those days that took us easily 4-5 minutes for a 20 Neuron network. SVM and some of the other techniques were in experimental phase at that time!
After graduating with my PhD I started working in the industry and kept on following the advancements in data science, both algorithmically and computationally. I have been part of many industrial applications where predictions were used to improve the quality of many goods you use every day. From the pet-food you use to feed your pets to the polyester used to make some of the clothes you are wearing.
I am still an industrial practitioner, however now it is very rare that I do the work myself but I have a group of engineers and scientists that amongst other things do some data science work under my supervision.
I really like how data science has evolved and I am fascinated that I can now do on my Mac in under 1 minute calculations that used to take several minutes on a Unix SPARC station ;)