Pith. sign in

REVIEW 22 cited by

Continual Learning and Catastrophic Forgetting

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.05175 v1 pith:CMXRPNHW submitted 2024-03-08 cs.LG cs.AIcs.CVq-bio.NCstat.ML

classification cs.LGcs.AIcs.CVq-bio.NCstat.ML
keywords learningcontinualbookcatastrophicchapterforgettingnetworksalthough
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This book chapter delves into the dynamics of continual learning, which is the process of incrementally learning from a non-stationary stream of data. Although continual learning is a natural skill for the human brain, it is very challenging for artificial neural networks. An important reason is that, when learning something new, these networks tend to quickly and drastically forget what they had learned before, a phenomenon known as catastrophic forgetting. Especially in the last decade, continual learning has become an extensively studied topic in deep learning. This book chapter reviews the insights that this field has generated.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 22 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning

    cs.LG 2026-08 conditional novelty 7.0 of 10

    A layer-wise information-theoretic decomposition bounds replay-based continual learning's generalization gap, predicting memory scaling, an interior stabilization layer, and gradient-alignment signals that track forgetting.

  2. Mind the Context: Continual Learning of Socially Appropriate Robot Actions via Environmental-Social Disentanglement

    cs.RO 2026-08 conditional novelty 6.0 of 10

    EDD splits scene images into environmental and social-agent views, trains a dual-branch network with replay, and improves prediction of socially appropriate robot actions across six indoor domains in a domain-incremen...

  3. BPG: Balancing Plasticity and Generalization for Domain Incremental Learning

    cs.CV 2026-08 conditional novelty 6.0 of 10

    BPG sizes per-domain adapters inversely to a feature-separability score and replaces hard domain selection with confidence-weighted logit fusion, setting state-of-the-art accuracy and near-zero forgetting on three dom...

  4. Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning

    cs.LG 2026-01 unverdicted novelty 6.0 of 10

    Reinforcement learning learns state-dependent parametrization components in idealized climate models that outperform static tuning across several testbeds.

  5. Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity

    cs.NE 2025-12 conditional novelty 6.0 of 10

    A gradient-trained control network whose size adjusts online through a local structural plasticity module matches or beats fixed-size MLPs on three control benchmarks.

  6. ReclAIm: A Multi-Agent Framework for Monitoring and Correcting Performance Decline in Medical Imaging AI

    cs.MA 2025-10 conditional novelty 6.0 of 10

    A natural-language multi-agent framework automatically detected performance declines in medical image classifiers and recovered most lost accuracy by fine-tuning.

  7. Genesis: A Spiking Neuromorphic Accelerator With On-chip Continual Learning

    cs.NE 2025-09 conditional novelty 6.0 of 10

    A 65nm spiking chip, Genesis, learns five MNIST digit-pair tasks sequentially with 74.46% mean accuracy at 17.08 mW, using metaplasticity to fight catastrophic forgetting.

  8. Evolution, Future of AI, and Singularity

    cs.OH 2025-06 conditional novelty 6.0 of 10

    The paper translates principles from evolutionary developmental biology into a new AI design paradigm that promises continual learning, structured representations, and a grounded path to technological singularity.

  9. Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence

    cs.AI 2025-06 conditional novelty 6.0 of 10

    The paper proposes regulatory connections, weak linkage, and component-level variation-selection, drawn from evo-devo, as the unifying conceptual foundation for a new AI design paradigm.

  10. Privacy-Aware Lifelong Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    PALL learns tasks in a single network as sparse subnetworks and performs exact task unlearning by resetting the task's trained parameters and briefly retraining shared ones from a rehearsal buffer.

  11. Quo Vadis, World Modeling?

    cs.CV 2026-08 conditional novelty 5.0 of 10

    An agent-centric reframing of world modeling, replacing physical state prediction with 'information transitions' organized into six proxy functions and three empowerment levels.

  12. Gated Adaptation for Continual Learning in Human Activity Recognition

    cs.LG 2026-03 conditional novelty 5.0 of 10

    Channel-wise gating of frozen pretrained features reduces catastrophic forgetting in subject-incremental HAR, reaching ~78% final accuracy on PAMAP2 versus ~57% for full fine-tuning.

  13. An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning

    cs.LG 2025-09 conditional novelty 5.0 of 10

    ACED-DQN combines heterogeneous DQN variants with loss-based reliability weighting and experience assignment, but the paper's own ablation indicates that arbitration control is not the key factor behind the performance gain.

  14. Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Neuron-Fusion selectively restores large-change neurons from a fine-tuned multimodal model and suppresses small changes, improving language retention with modest visual trade-offs.

  15. On the Parallels Between Evolutionary Theory and the State of AI

    q-bio.NC 2025-05 conditional novelty 5.0 of 10

    The authors propose that evolutionary developmental biology's principles, such as encapsulation, regulatory control, and local variation-selection, can overcome continual learning and explainability limits of current ...

  16. Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculture

    cs.LG 2025-04 conditional novelty 5.0 of 10

    A prototype-based audio-visual continual learning method, HAIL-FFIA, reaches 75.92% average accuracy on a new six-species fish-feeding dataset while storing only 0.1% of raw data.

  17. Continual Learning with Columnar Spiking Neural Networks

    cs.NE 2025-06 conditional novelty 4.0 of 10

    A columnar spiking neural network with local learning rules reaches 92% average accuracy and about 4% forgetting on ten permuted-MNIST tasks, but only when tasks share no features.

  18. Replay to Remember (R2R): An Efficient Uncertainty-driven Unsupervised Continual Learning Framework Using Generative Replay

    cs.CV 2025-05 reject novelty 4.0 of 10

    R2R reaches 98.13% on CIFAR-10 and 59.74% on TinyImageNet by replaying diffusion-generated samples for uncertain clusters, but its no-pretraining claim conflicts with its use of pretrained Stable Diffusion, CLIP, and ...

  19. Efficient Sensorimotor Learning for Open-world Robot Manipulation

    cs.RO 2025-05 conditional novelty 4.0 of 10

    A PhD dissertation argues that object, spatial, and behavioral regularities, extracted with foundation models, enable data-efficient, generalizable robot manipulation, and presents seven systems and a benchmark built ...

  20. CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey

    cs.CV 2025-04 conditional novelty 4.0 of 10

    CLIP-powered domain generalization and domain adaptation methods are surveyed and categorized into prompt-learning versus backbone use, and source-available versus source-free settings.

  21. Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation

    cs.CV 2025-01 conditional novelty 4.0 of 10

    Fine-tuning a pretrained vision model with only 2-6% of its LoRA adapters active preserves zero-shot and out-of-distribution performance while matching full-rank LoRA accuracy.

  22. Distributed Learning and Inference Systems: A Networking Perspective

    cs.LG 2025-01 conditional novelty 4.0 of 10

    DA-ITN organizes distributed ML training and inference into network layers with routing-aware topologies, but the paper provides no implementation or evaluation.

Pith tools