REVIEW 17 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
Continual Learning and Catastrophic Forgetting
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 17 Pith papers
-
Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization
ISI-CV derives a synaptic importance score from the regularity of neuron firing intervals to enable continual learning without gradients or forgetting on SNNs.
-
Optimal L2 Regularization in High-dimensional Continual Linear Regression
In high-dimensional continual linear regression, optimal fixed L2 regularization strength scales as T/ln T with the number of tasks and mitigates label noise for arbitrary linear teachers.
-
McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware
McNdroid is a new longitudinal multimodal benchmark showing that Android malware detectors degrade over time but multimodal approaches maintain better performance across long temporal gaps.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
-
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.
-
Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs
AIR augments activation-aware SVD compression of LLMs with an influence metric and a closed-form ALS update, claiming >18% perplexity improvement at 60% parameter retention and 90% less calibration data than SVD-LLM(W).
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
-
HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigati...
-
An empirical evaluation of the risks of AI model updates using clinical data: stability, arbitrariness, and fairness
Updating clinical AI models can cause prediction flips, arbitrariness, and unfair error rates across groups, requiring dedicated monitoring dimensions.
-
ALAS: Adaptive Long-Horizon Action Synthesis via Async-pathway Stream Disentanglement
ALAS disentangles environment and self-state streams via bio-inspired modules to deliver 23% higher subtask success and 29% better execution efficiency on long-horizon HSI tasks.
-
Task Switching Without Forgetting via Proximal Decoupling
Operator splitting separates task optimization from proximal stability enforcement to achieve forgetting-free continual learning with SOTA benchmark results.
-
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.
-
Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning
Reinforcement-learned policies that set model parameters as a function of model state reduce temperature bias in three idealised climate testbeds, but only when evaluated on the same climatology used for training.
-
Toward decision-aware AI for LSST-scale time-domain astronomy
Proposes foundation models and decision-theoretic policies to manage evolving source representations and optimize follow-up resource allocation in LSST-scale time-domain astronomy.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.