article · International Journal of Artificial Intelligence Tools · 2019
An Efficient Perpetual Learning Algorithm
Haiou Qin, Du Zhang, Xibin Sun, Jiahua Tang, Jun Peng
Cited by 1Abstract and details only
Abstract
One of the emerging research opportunities in machine learning is to develop computing systems that learn many tasks continuously and improve the performance of learned tasks incrementally over time. In real world, learners have to adapt to labeled and unlabeled samples from various tasks which arrive randomly. In this paper, we propose an efficient algorithm called Efficient Perpetual Learning Algorithm (EPLA) which is suitable for learning multiple tasks in both offline and online settings. The algorithm, which is an extension of ELLA,4 is part of what we call perpetual learning that can learn new tasks or refine knowledge of learned tasks for improved performance with newly arrived labeled samples in an incremental fashion. Several salient features exist for EPLA. The learning episodes are triggered via either extrinsic or intrinsic stimuli. Agent systems based on the proposed algorithm can be engaged in an open-ended and alternating sequence of learning episodes and working episodes. Unlabeled samples can be used to self-train the learner in small data setting. Compared with ELLA, EPLA shows almost equivalent performance without memorizing any labeled samples learned previously.
Cite this paper
Qin, H., Zhang, D., Sun, X., Tang, J., & Peng, J. (2019). An Efficient Perpetual Learning Algorithm. International Journal of Artificial Intelligence Tools, 28(07), 1950022. https://doi.org/10.1142/s0218213019500222
Qin, Haiou, et al. “An Efficient Perpetual Learning Algorithm.” International Journal of Artificial Intelligence Tools, vol. 28, no. 07, 2019, p. 1950022, https://doi.org/10.1142/s0218213019500222.
Qin, Haiou, Du Zhang, Xibin Sun, Jiahua Tang, and Jun Peng. 2019. “An Efficient Perpetual Learning Algorithm.” International Journal of Artificial Intelligence Tools 28 (07): 1950022. https://doi.org/10.1142/s0218213019500222.
Qin, H. et al. (2019) ‘An Efficient Perpetual Learning Algorithm’, International Journal of Artificial Intelligence Tools, 28(07), p. 1950022. Available at: https://doi.org/10.1142/s0218213019500222.
@article{qin2019efficient,
title = {{An Efficient Perpetual Learning Algorithm}},
author = {Qin, Haiou and Zhang, Du and Sun, Xibin and Tang, Jiahua and Peng, Jun},
journal = {International Journal of Artificial Intelligence Tools},
volume = {28},
number = {07},
pages = {1950022},
year = {2019},
doi = {10.1142/s0218213019500222}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.