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
Signed reviews
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.
Forward citations
Cited by 22 Pith papers
-
Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning
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.
-
Mind the Context: Continual Learning of Socially Appropriate Robot Actions via Environmental-Social Disentanglement
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...
-
BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
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...
-
Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning
Reinforcement learning learns state-dependent parametrization components in idealized climate models that outperform static tuning across several testbeds.
-
Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity
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.
-
ReclAIm: A Multi-Agent Framework for Monitoring and Correcting Performance Decline in Medical Imaging AI
A natural-language multi-agent framework automatically detected performance declines in medical image classifiers and recovered most lost accuracy by fine-tuning.
-
Genesis: A Spiking Neuromorphic Accelerator With On-chip Continual Learning
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.
-
Evolution, Future of AI, and Singularity
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.
-
Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence
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.
-
Privacy-Aware Lifelong Learning
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.
-
Quo Vadis, World Modeling?
An agent-centric reframing of world modeling, replacing physical state prediction with 'information transitions' organized into six proxy functions and three empowerment levels.
-
Gated Adaptation for Continual Learning in Human Activity Recognition
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.
-
An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning
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.
-
Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs
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.
-
On the Parallels Between Evolutionary Theory and the State of AI
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 ...
-
Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculture
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.
-
Continual Learning with Columnar Spiking Neural Networks
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.
-
Replay to Remember (R2R): An Efficient Uncertainty-driven Unsupervised Continual Learning Framework Using Generative Replay
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 ...
-
Efficient Sensorimotor Learning for Open-world Robot Manipulation
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 ...
-
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
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.
-
Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation
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.
-
Distributed Learning and Inference Systems: A Networking Perspective
DA-ITN organizes distributed ML training and inference into network layers with routing-aware topologies, but the paper provides no implementation or evaluation.
Discussion (0). Continue with ORCID to comment.