Three Components of Machine Learning - Data
Data is the fuel of machine learning methods. We can think of data as collections of many elementary units which we call data points. Data points can represent persons, images, movies, molecules, antenna signal, vibration sensors or random variables.
Each data point is characterized by different properties which we divide into two different types of properties: features and labels. Features are low-level properties that can be measured with low effort. Labels are high-level properties, or quantities of interest, that cannot be measured easily. The ultimate goal of machine learning is to predict the labels of data points based solely on their features.
Read more about how data is used in machine learning in Chapter 2 of http://mlbook.cs.aalto.fi
Watch video Three Components of Machine Learning - Data online without registration, duration hours minute second in high quality. This video was added by user Alexander Jung 14 December 2019, don't forget to share it with your friends and acquaintances, it has been viewed on our site 2,004 once and liked it 13 people.