How to make a machine learn continuously: a tutorial of the Bayesian approach

Khoat Than; Xuan Bui; Tung Nguyen-Trong; Khang Truong; Son Nguyen; Bach Tran; Linh Ngo Van; Anh Nguyen-Duc

doi:10.1117/12.2518860

10 May 2019 How to make a machine learn continuously: a tutorial of the Bayesian approach

Khoat Than, Xuan Bui, Tung Nguyen-Trong, Khang Truong, Son Nguyen, Bach Tran, Linh Ngo Van, Anh Nguyen-Duc

Proceedings Volume 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications; 110060I (2019) https://doi.org/10.1117/12.2518860
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

How to build a machine that can continuously learn from observations in its life and make accurate inference/prediction? This is one of the central questions in Artificial Intelligence. Many challenges are present, such as the difficulty of learning from infinitely many observations (data), the dynamic nature of the environments, noisy and sparse data, the intractability of posterior inference, etc. This tutorial will discuss how the Bayesian approach provides a natural and efficient answer. We will start from the basic of Bayesian models, and then the variational Bayes method for inference. Next, we will discuss how to learn a Bayesian model from an infinite sequence of data. Some challenges such as catastrophic forgetting phenomenon, concept drifts, and overfitting will be discussed.

Conference Presentation

Citation Download Citation

Khoat Than, Xuan Bui, Tung Nguyen-Trong, Khang Truong, Son Nguyen, Bach Tran, Linh Ngo Van, and Anh Nguyen-Duc "How to make a machine learn continuously: a tutorial of the Bayesian approach", Proc. SPIE 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 110060I (10 May 2019); https://doi.org/10.1117/12.2518860

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available