Home // VISUAL 2017, The Second International Conference on Applications and Systems of Visual Paradigms // View article

Visual Deep Learning Recommender System for Personal Computer Users

Authors:
Daniel Shapiro
Hamza Qassoud
Mathieu Lemay
Miodrag Bolic

Keywords: Recommender systems; Image processing; Deep learning

Abstract:
This work presents a new architecture for creating virtual assistants on personal computers, building upon prior work on deep learning neural networks, image processing, mixed-initiative systems, and recommender systems. Recent progress in virtual assistants enables them to converse with users and interpret what the user sees. These systems can understand the world in intuitive ways with neural networks, and make action recommendations to the user. The assistant architecture in this work is described at the component level. It interprets a computer screen image in order to 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: 1 to 10

Copyright: Copyright (c) IARIA, 2017

Publication date: July 23, 2017

Published in: conference

ISSN: 2519-8645

ISBN: 978-1-61208-577-7

Location: Nice, France

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