Under copyright Constraint(s) on Use: This work is protected by the U.S. Copyright Law (Title 17, U.S.C.). Use of this work beyond that allowed by "fair use" or any license applied to this work requires written permission of the copyright holder(s). Responsibility for obtaining permissions and any use and distribution of this work rests exclusively with the user and not the UC San Diego Library. Inquiries can be made to the UC San Diego Library program having custody of the work. Use: This work is available from the UC San Diego Library. This digital copy of the work is intended to support research, teaching, and private study.
Rights Holder and Contact
Gorlla, Cyril; Thach, Jared; Hoshida, Hiroki
Description
Caption: An algorithm inspired by biological neuronal structure learns how to predict unseen human behavior Participant category: Undergraduate student Department: Halıcıoğlu Data Science Institute The point at which the seemingly innocuous red line crosses under the blue represents something magnificent—an artificial neural network performing better on data consisting of unseen human behavior than the data it was trained on. This indicates that the algorithm has truly "learned" the underlying behavior patterns of the people in the data. The simplistic beauty in these two unassuming lines was the product of a research collaboration between the Halıcıoğlu Data Science Institute and Intel, wherein our team sought to predict PC user behavior in order to preemptively load applications. By preloading applications a user would likely use, we were able to improve overall system fluidity, which is especially important for those without access to newer, higher end PC hardware. This image shows the performance of a LSTM model, a neural network based on a structure of connected memory blocks. Over the course of a day, this model was able to predict the duration a user would use a given app within 45 seconds. The blue line indicates the model's performance on training data, while the red line indicates its performance on unseen data (where lower values indicate a more accurate model). Research Data Curation Program, UC San Diego, La Jolla, 92093-0175 (https://lib.ucsd.edu/rdcp) Gorlla, Cyril; Thach, Jared; Hoshida, Hiroki (2022). When a Machine 'Learns'. In Art of Science. UC San Diego Library Digital Collections. https://doi.org/10.6075/J0TM7B8G
Type
image
Identifier
ark:/20775/bb83034649
Language
No linguistic content
Subject
Neural networks (Computer science) Machine learning Art and science Art of Science Contest - 2022
If you're wondering about permissions and what you can do with this item, a good starting point is the "rights information" on this page. See our terms of use for more tips.
Share your story
Has Calisphere helped you advance your research, complete a project, or find something meaningful? We'd love to hear about it; please send us a message.
