Home // INTELLI 2017, The Sixth International Conference on Intelligent Systems and Applications // View article

Unsupervised Deep Learning Recommender System for Personal Computer Users

Authors:
Daniel Shapiro
Hamza Qassoud
Mathieu Lemay
Miodrag Bolic

Keywords: Recommender systems; Unsupervised learning; Deep learning

Abstract:
This work presents an unsupervised learning approach for training a virtual assistant recommender system, building upon prior work on deep learning neural networks, image processing, mixed-initiative systems, and recommender systems. Intelligent agents can understand the world in intuitive ways with neural networks, and make action recommendations to computer users. The system discussed in this work interprets a computer screen image in order to learn new keywords from the user’s screen and associate them to new contexts in a completely unsupervised way, then produce action recommendations to assist the user. It can assist in automating various tasks such as genetics research, computer programming, engaging with social media, and legal research. The action recommendations are personalized to the user, and are produced without integration of the assistant into each individual application executing on the computer. Recommendations can be accepted with a single mouse click by the computer user.

Pages: 22 to 31

Copyright: Copyright (c) IARIA, 2017

Publication date: July 23, 2017

Published in: conference

ISSN: 2308-4065

ISBN: 978-1-61208-576-0

Location: Nice, France

Dates: from July 23, 2017 to July 27, 2017