Machine Learning for Smart Cities

Aim

In this course, you will learn how to utilize advanced models and deep learning architectures to learn from data in order to gain insights for decisions in smart city applications.

After completing the course, the student should be able to:

• Explain assumptions and theory behind different type of machine learning methods
• Explain and motivate differences in characteristics between different type of methods and give examples of when they should be applied
• Evaluate and choose among different methods for a specific problem instance and dataset
• Use existing datasets to train and evaluate different machine learning models
• Use selected machine learning models for prediction, inference and decision-making for smart city applications

Content

The course aims to provide knowledge in machine learning. The course will cover both conventional machine learning methods as well as deep learning. The course content includes statistical inference, bias-variance tradeoff, Bayesian learning, Gaussian processes, support vector machines, kernels, neural networks, deep learning and reinforcement learning.