Papers on Anton Leehttps://tachyonicclock.github.io/papers/Recent content in Papers on Anton LeeHugoen-usMon, 15 Sep 2025 00:00:00 +0000Machine Learning for Data Streams with CapyMOAhttps://tachyonicclock.github.io/papers/conf_pkdd_sunglgclhcbkpb25/Mon, 15 Sep 2025 00:00:00 +0000https://tachyonicclock.github.io/papers/conf_pkdd_sunglgclhcbkpb25/Kolmogorov-Arnold Networks Still Catastrophically Forget but Differently from MLPhttps://tachyonicclock.github.io/papers/conf_aaai_leegzk25/Tue, 25 Feb 2025 00:00:00 +0000https://tachyonicclock.github.io/papers/conf_aaai_leegzk25/CapyMOA: Efficient Machine Learning for Data Streams in Pythonhttps://tachyonicclock.github.io/papers/corr_abs-2502-07432/Sat, 01 Feb 2025 00:00:00 +0000https://tachyonicclock.github.io/papers/corr_abs-2502-07432/CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learninghttps://tachyonicclock.github.io/papers/corr_abs-2501-11140/Wed, 01 Jan 2025 00:00:00 +0000https://tachyonicclock.github.io/papers/corr_abs-2501-11140/Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learninghttps://tachyonicclock.github.io/papers/conf_cikm_leezgbp23/Sat, 21 Oct 2023 00:00:00 +0000https://tachyonicclock.github.io/papers/conf_cikm_leezgbp23/Balancing the Stability-Plasticity Dilemma with Online Stability Tuning for Continual Learninghttps://tachyonicclock.github.io/papers/conf_ijcnn_leegz22/Mon, 18 Jul 2022 00:00:00 +0000https://tachyonicclock.github.io/papers/conf_ijcnn_leegz22/Balancing the stability-plasticity dilemma is an omnipresent challenge in continual learning. The dilemma is that the ability of a model to learn new knowledge (plasticity) comes at the expense of the ability to remember past knowledge (stability) and vice versa. Some continual learning algorithms incorporate a constant hyper-parameter to control this trade-off. We argue that the trade-off should be dynamically tuned rather than kept constant. We propose a method to dynamically balance stability and plasticity in a semi-online and fully online manner.