Introduction

Machine Learning is all about Data Analytics, complex Mathematical Models and Algorithms, used for Predictive Analytics. Machine learning is closely related to (and often overlaps with) computational statistics, which also focuses on prediction-making through the use of computers. It has strong ties to mathematical optimization.

Machine Learning is about examine large amount of data (“Big Data”) looking for Patterns.
It applies statistical techniques to large amounts of data, looking for the best pattern to solve your problem. This pattern can be referred to as a data model.
The machine learning process starts with raw data and ends up with a model derived from that data.
The machine learning algorithm is run on prepared data, and the result is referred to as a model.
The knowledge gained is then used for Predictions, i.e., Predict the Future Machine Learning is an iterative process, which continuously updates the model when new data/knowledge arrives.

A simplified sketch of the Machine Learning process:

Machine Learning Applications:

Create complex Weather models from a large amount of collected weather data. The weather models are then used to predict the weather in the future (short or long termed)
Transportation: Self driving cars, ships or so-called Autonomous vehicles
Marketing and sales, e.g., Online recommendation offers such as those from Amazon and Netflix
Apple Siri (intelligent personal assistant) and similar services
Financial services, such as Stock market, etc.
... hundreds of other examples

Video Introducing Machine Learning:

Machine Learning in Automation Systems

In Automation Systems we have used well known “Machine Learning” principles such as System Identification, State Estimation with Kalman Filter and Model Predictive Control (MPC) for many years now.

Se also the video Machine Learning in Automation Systems:

In this example more traditional and well known Machine Learning principles such as System Identification, State Estimation with Kalman Filter and Model Predictive Control, and how these techniques can be seen in the wider concept of Machine Learning.

For more detals, see Machine Learning in Automation Systems.

See Automation and Control for more information about System Identification, State Estimation with Kalman Filter and Model Predictive Control (MPC).