“Introduction to Machine Learning in Julia: New course launch”
In 2022, I completed my PhD from MIT in experimental Electrical and Mechanical Engineering. While much of my research was hands-on, I discovered the unique power of Scientific Machine Learning through Julia, and I found Julia to be exceptionally suited for solving complex scientific problems.
I started using Julia to integrate ML into my research, which led to some high-impact findings. Recently, two of the research papers were accepted to the NeurIPS workshops, one exploring human vs. AI text classification and another predicting outcomes with the Chandrasekhar white dwarf equation.
Most online courses teach ML with Python, but Julia offers a specialized advantage in scientific machine learning. Many real-world problems remain unexplored, especially within scientific domains, where Julia can make things easy for you.
For the last 4 months, I have been working on a new course, “Introduction to Machine Learning in Julia”. This ~20-hour course will start from scratch, guiding you through the essentials of Julia and implementing ML models, plus some deep learning.
The course has five modules:
- Basics of Julia Programming – from installation to basic operations and loops.
- Data Science in Julia – covering data cleanup, visualization, and statistical analysis.
- Machine Learning in Julia – from linear regression to clustering, decision trees, and random forests.
- Deep Learning in Julia – an introduction to neural networks and time series analysis.
- Capstone Project – a hands-on project to consolidate learning and apply skills in a real-world problem.
This course is aimed at both students exploring ML and industry professionals looking to build impactful ML applications. Julia may be niche, but for anyone serious about scientific ML, it is a powerful tool to add to your skill set.
I encourage you to join us in this journey of learning Julia for machine learning.