Introduction to Machine Learning for Real World Solutions
2-Day Workshop | Next course: coming soon
Price: $800 (Full-time students $600)
Machine learning (ML) is a field of artificial intelligence (AI) in which computer algorithms “learn” to perform pattern recognition on data. In today’s world, ML has strong use cases in a wide variety of applications, ranging from customer profiling to medical diagnosis.
In this 2-day practical introduction to ML, you will get hands-on experience with the core set of ML algorithms used extensively by industry leaders. Through a series of core concept sessions and practical tasks, you will develop an understanding of how to apply advanced ML algorithms for a range of different applications.
The course first provides an introduction to key concepts in AI, including identifying the strengths of ML and where it is best applied to solve a problem. Further concepts focus on defining challenging problems based on ML methods and understanding which ML method is ideal to the specific data you have and solution required. We will then work with you to build practical knowledge of how to select, apply and evaluate advanced ML algorithms for a range of different applications. This will involve you choosing the best approach, cleaning your data, training the algorithms and, finally, evaluating the success of your ML models.
At the end of this course, you will have a solid foundation of core ML concepts on which to continue building your expertise and an intuition for how ML can be applied to solve for real-world problems.
Prerequisites: You must have an understanding of Python to successfully complete this course
Key skills participants will learn from this course:
- Navigating the core ML and data science libraries in Python
- Defining your ML approach according to your desired solution
- Understanding which algorithms are most suitable
- Cleaning and preparation of data in readiness for ML
- Evaluating the success of your solution
- Applications of artificial intelligence
- What is artificial intelligence, machine learning, and deep learning
- The key skills to effectively use ML on your problem
- Core Python libraries for machine learning, including Numpy, Matplotlib, Scikit-Learn and Pandas
- Understanding why data cleaning and structuring is vital, including best practice
- Tools for appropriately structuring your data for your ML algorithm
- Consolidation of these concepts with a Jupyter notebook example
- Get hands-on practice with a raw dataset. You will have to employ the techniques you have learnt to clean and structure data in readiness for ML.
- Supervised learning categories; continuous vs. discrete predictions
- Unsupervised learning; identifying hidden patterns or knowledge discovery through clustering
- Coding examples with classification, regression, and clustering models
- Why solid model evaluation is imperative for the ML practitioner
- Established performance metrics, and how to implement them
- Model cross-validation and ensembles
- Introduction to representation Learning models with implementation examples
- Using the preprocessed data from Day 1, explore how the various ML models behave on the dataset. By the end of this final challenge, you will have built a ML solution from start to finish!
Sean did his PhD in robotic vision at the Australian Centre for Robotic Vision, QUT, and holds a Bachelor’s degree in mechatronics. Sean’s PhD focused on training deep convolutional neural networks (CNNs) for autonomous hazard detection on construction sites. Sean has presented his research in both domestic and international conferences and taught numerous workshops on AI. He also acts a community mentor, teaching beginners and advanced deep learning courses.
Seun is a PhD candidate in the Smart Machines Group, UQ, where he focuses on developing artificial intelligence-driven predictive maintenance for complex systems. He is also part of the Asset Management Group at the University of Cambridge. He also holds a Master of Science from Carnegie Mellon University and has over three years’ experience as an academic tutor in engineering and technology courses.