Addressing catastrophic forgetting in payload parameter identification using incremental ensemble learning [PDF]
Frontiers in Robotics and AICollaborative robots (cobots) are increasingly integrated into Industry 4.0 dynamic manufacturing environments that require frequent system reconfiguration due to changes in cobot paths and payloads. This necessitates fast methods for identifying payload
Khaled Elgeneidy +2 more
exaly +4 more sources
Catastrophic Forgetting in Deep Graph Networks: A Graph Classification Benchmark [PDF]
Frontiers in Artificial Intelligence, 2022 In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a ...
Federico Errica +2 more
exaly +4 more sources
Sleep prevents catastrophic forgetting in spiking neural networks by forming a joint synaptic weight representation. [PDF]
PLoS Computational Biology, 2022 Artificial neural networks overwrite previously learned tasks when trained sequentially, a phenomenon known as catastrophic forgetting. In contrast, the brain learns continuously, and typically learns best when new training is interleaved with periods of
Ryan Golden +3 more
doaj +2 more sources
Model architecture can transform catastrophic forgetting into positive transfer [PDF]
Scientific Reports, 2022 The work of McCloskey and Cohen popularized the concept of catastrophic interference. They used a neural network that tried to learn addition using two groups of examples as two different tasks.
Miguel Ruiz-Garcia
doaj +2 more sources
Can sleep protect memories from catastrophic forgetting? [PDF]
eLife, 2020 Continual learning remains an unsolved problem in artificial neural networks. The brain has evolved mechanisms to prevent catastrophic forgetting of old knowledge during new training.
Oscar C González +4 more
doaj +2 more sources
Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks. [PDF]
PLoS ONE, 2017 A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is when learning
Roby Velez, Jeff Clune
doaj +2 more sources
Catastrophic Forgetting, Rehearsal and Pseudorehearsal [PDF]
Connection Science, 1995 This paper reviews the problem of catastrophic forgetting (the loss or disruption of previously learned information when new information is learned) in neural networks, and explores rehearsal mechanisms (the retraining of some of the previously learned information as the new information is added) as a potential solution.
Anthony Robins
exaly +2 more sources
Overcoming catastrophic forgetting in neural networks. [PDF]
Proc Natl Acad Sci U S A, 2017 Significance Deep neural networks are currently the most successful machine-learning technique for solving a variety of tasks, including language translation, image classification, and image generation. One weakness of such models is that, unlike humans, they are unable to learn multiple tasks sequentially.
Kirkpatrick J +13 more
europepmc +6 more sources
Array heterogeneity prevents catastrophic forgetting in infants. [PDF]
Cognition, 2015 Working memory is limited in adults and infants. But unlike adults, infants whose working memory capacity is exceeded often fail in a particularly striking way: they do not represent any of the presented objects, rather than simply remembering as many objects as they can and ignoring anything further (Feigenson & Carey, 2003, 2005).
Zosh JM, Feigenson L.
europepmc +4 more sources
Bayesian continual learning and forgetting in neural networks [PDF]
Nature CommunicationsBiological synapses effortlessly balance memory retention and flexibility, yet artificial neural networks still struggle with the extremes of catastrophic forgetting and catastrophic remembering.
Djohan Bonnet +6 more
doaj +2 more sources