Memory retention--the synaptic stability versus plasticity dilemma.

By Wickliffe C. Abraham, Anthony V. Robins. 2005

389 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience, Electrical and Electronic Engineering, Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cellular and Molecular Neuroscience

In Cognitive Neuroscience

In Electrical and Electronic Engineering

In Neuroscience

Citations in the corpus

Continual Learning with Deep Generative Replay (2017, background): “This flexible memory system results from a good balance between synaptic plasticity and stability [1].”
FearNet: Brain-Inspired Model for Incremental Learning (2017, background): “Catastrophic forgetting in DNNs occurs due to the plasticity-stability dilemma (Abraham & Robins, 2005).”
Measuring Catastrophic Forgetting in Neural Networks (2017, background): “Catastrophic forgetting in neural networks occurs because of the stability-plasticity dilemma (Abraham and Robins 2005).”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “If learning occurs continuously, i.e. online, new information or skills have the potential to overwrite previously acquired information or skills (Abraham and Robins, 2005).”
Short-term plasticity as cause–effect hypothesis testing in distal reward learning (2014, background): “(Abraham and Robins, 2005), and therefore preserved as memory.”
Synaptic weight decay with selective consolidation enables fast learning without catastrophic forgetting (2019, background): “This problem is known as the stability-plasticity dilemma, and mechanisms at the network and synapse level have been proposed to tackle it (Abraham and Robins, 2005; Fusi et al., 2005; Carpenter and Grossberg, 1988).”
Memory Efficient Experience Replay for Streaming Learning (2018, background): “Catastrophic forgetting is a result of the stability-plasticity dilemma [1]; that is, the network must maintain a balance between plasticity”
Continual Normalization: Rethinking Batch Normalization for Online Continual Learning (2022, background): “Therefore, they have to achieve a good trade-off between retaining old knowledge (French, 1999) and acquiring new skills, which is referred to as the stability-plasticity dilemma (Abraham & Robins, 2005).”
Few-Shot and Continual Learning with Attentive Independent Mechanisms (2021, background): “It is conjectured that the cause of catastrophic forgetting and inefficiency in learning new tasks is from the stability-plasticity dilemma [2].”
Replay in Deep Learning: Current Approaches and Missing Biological Elements (2021, neutral): “However, when the training set evolves in a nonstationary manner or the agent learns from a sequence of experiences, gradient descent updates to the network cause catastrophic forgetting of previously learned knowledge (McCloskey & Cohen, 1989; Abraham & Robins, 2005).”
Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis (2019, background): “Incrementally updating a DNN is challenging due to the stability-plasticity dilemma [1].”
An Adaptive Random Path Selection Approach for Incremental Learning. (2019, background): “This highlights the stability-plasticity dilemma in neural networks [10] i.e., a rigid and stable model will not be able to learn new concepts while an easily adaptable model is susceptible to forget old concepts due to major parameter changes.”
About sleep's role in memory. (2013, neutral): “[PDF] [Full Text] [Abstract] , June , 2014; 20 (3): 203-219.”
Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks (2018, background): “Solutions to CF can be aligned with the biological learning notions of synaptic stability and plasticity [3].”
Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting (2018, background): “The synaptic plasticity hypothesis [21] states that the weights between the units can change as long the output units still produce the correct output pattern.”