Learning to Learn: How to Continuously Teach Humans and Machines

Page view(s)
26
Checked on Oct 04, 2024
Learning to Learn: How to Continuously Teach Humans and Machines
Title:
Learning to Learn: How to Continuously Teach Humans and Machines
Journal Title:
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Keywords:
Publication Date:
15 January 2024
Citation:
Singh, P., Li, Y., Sikarwar, A., Lei, W., Gao, D., Talbot, M. B., Sun, Y., Shou, M. Z., Kreiman, G., & Zhang, M. (2023, October 1). Learning to Learn: How to Continuously Teach Humans and Machines. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.01075
Abstract:
Curriculum design is a fundamental component of education. For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication. These and other concepts must be mastered before our first algebra lesson, which also reinforces our addition and multiplication skills. Designing a curriculum for teaching either a human or a machine shares the underlying goal of maximizing knowledge transfer from earlier to later tasks, while also minimizing forgetting of learned tasks. Prior research on curriculum design for image classification focuses on the ordering of training examples during a single offline task. Here, we investigate the effect of the order in which multiple distinct tasks are learned in a sequence. We focus on the online class-incremental continual learning setting, where algorithms or humans must learn image classes one at a time during a single pass through a dataset. We find that curriculum consistently influences learning outcomes for humans and for multiple continual machine learning algorithms across several benchmark datasets. We introduce a novel-object recognition dataset for human curriculum learning experiments and observe that curricula that are effective for humans are highly correlated with those that are effective for machines. As an initial step towards automated curriculum design for online class-incremental learning, we propose a novel algorithm, dubbed Curriculum Designer (CD), that designs and ranks curricula based on inter-class feature similarities. We find significant overlap between curricula that are empirically highly effective and those that are highly ranked by our CD. Our study establishes a framework for further research on teaching humans and machines to learn continuously using optimized curricula.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - AI Singapore
Grant Reference no. : AISG2-RP-2021-025

This research / project is supported by the Agency for Science, Technology, and Research (A*STAR) - Startup Grant
Grant Reference no. : NA

This research / project is supported by the Center for Frontier AI Research (CFAR) - Early Career Investigatorship
Grant Reference no. : NA

This research / project is supported by the National Research Foundation - NRF Fellowship
Grant Reference no. : NRF-NRFF15-2023-0001

This research is supported by the National Science Foundation under grant number NSF CCF 1231216, the National Institutes of Health under grant number NIH R01EY026025, and the National Institute of General Medical Sciences under award number T32GM144273.
Description:
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1550-5499
Files uploaded:

File Size Format Action
singh-learning-to-learn-how-to-continuously-teach-humans-and-machines-iccv-2023-paperpdf-safe.pdf 1.42 MB PDF Request a copy