Abstract
Several decades of research in the field of machine learning have resulted in a multitude of different algorithms for solving a broad range of problems. To tackle a new application, a researcher typically tries to map their problem onto one of these existing methods, often influenced by their familiarity with specific algorithms and by the availability of corresponding software implementations. In this study, we describe an alternative methodology for applying machine learning, in which a bespoke solution is formulated for each new application. The solution is expressed through a compact modelling language, and the corresponding custom machine learning code is then generated automatically. This model-based approach offers several major advantages, including the opportunity to create highly tailored models for specific scenarios, as well as rapid prototyping and comparison of a range of alternative models. Furthermore, newcomers to the field of machine learning do not have to learn about the huge range of traditional methods, but instead can focus their attention on understanding a single modelling environment. In this study, we show how probabilistic graphical models, coupled with efficient inference algorithms, provide a very flexible foundation for model-based machine learning, and we outline a large-scale commercial application of this framework involving tens of millions of users. We also describe the concept of probabilistic programming as a powerful software environment for model-based machine learning, and we discuss a specific probabilistic programming language called Infer.NET, which has been widely used in practical applications.
Highlights
The origins of the field of machine learning go back at least to the middle of the last century
After summarizing the goals of model-based machine learning in §2, we show how these may be realized through the adoption of a Bayesian viewpoint (§3) coupled with probabilistic graphical models (§4) and deterministic approximate inference algorithms (§5)
We focus on a powerful framework based on Bayesian inference in probabilistic graphical models, and so we begin with a brief introduction to the Bayesian view of machine learning
Summary
The origins of the field of machine learning go back at least to the middle of the last century. Over the last decade in particular, there has been a rapid increase in the number of successful applications, ranging from web search to autonomous vehicles, and from medical imaging to speech recognition This has been driven by the increased availability of inexpensive computers, the development of improved machine learning algorithms, greater interest in the area from both the research community and the commercial sector, and most notably by the ‘data deluge’ characterized by an exponentially increasing quantity of data being gathered and stored on the world’s computers. A recent example of a very successful application of traditional machine learning is the skeletal tracking system in Kinect [2], which uses the signals from a depth video camera to perform realtime tracking of the full human skeleton on low-cost hardware It is based on a technique known as random forests of decision trees, and the training data consists of one million depth images of human body poses, each of which is labelled with body parts (right hand, left knee, etc.).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
