paper-with-me

Papers

Synaptic metaplasticity in binarized neural networks

2021-01-19 · Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin, Damien Querlioz

Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to "catastrophic forgetting": they rapidly forget the previous task when trained on a new one. Neuroscience suggests that biological synapses avoid this issue through the process of synaptic consolidation and metaplasticity: the plasticity itself changes upon repeated synaptic events. In this work, we show that this concept of metaplasticity can be transferred to a particular type of deep neural networks, binarized neural networks, to reduce catastrophic forgetting.

📄 PDF Abstract BibTeX arXiv:2101.07592

Code (1)

Laborieux-Axel/SynapticMetaplasticityBNN 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Synaptic Metaplasticity in Binarized Neural Networks

2020-03-07 · Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin, Damien Querlioz

While deep neural networks have surpassed human performance in multiple situations, they are prone to catastrophic forgetting: upon training a new task, they rapidly forget previously learned ones. Neuroscience studies, …

Bayesian Metaplasticity from Synaptic Uncertainty

2023-12-15 · Djohan Bonnet, Tifenn Hirtzlin, Tarcisius Januel, Thomas Dalgaty 외

Catastrophic forgetting remains a challenge for neural networks, especially in lifelong learning scenarios. In this study, we introduce MEtaplasticity from Synaptic Uncertainty (MESU), inspired by metaplasticity and Baye…

Bayesian InferenceContinual LearningLifelong learningPermuted-MNIST

Synaptic metaplasticity with multi-level memristive devices

2023-06-21 · Simone D'Agostino, Filippo Moro, Tifenn Hirtzlin, Julien Arcamone 외

Deep learning has made remarkable progress in various tasks, surpassing human performance in some cases. However, one drawback of neural networks is catastrophic forgetting, where a network trained on one task forgets th…

Superconducting Optoelectronic Neurons III: Synaptic Plasticity

2018-05-04 · Jeffrey M. Shainline, Adam N. McCaughan, Sonia M. Buckley, Christine A. Donnelly 외

As a means of dynamically reconfiguring the synaptic weight of a superconducting optoelectronic loop neuron, a superconducting flux storage loop is inductively coupled to the synaptic current bias of the neuron. A standa…

Theories of synaptic memory consolidation and intelligent plasticity for continual learning

2024-05-27 · Friedemann Zenke, Axel Laborieux

Humans and animals learn throughout life. Such continual learning is crucial for intelligence. In this chapter, we examine the pivotal role plasticity mechanisms with complex internal synaptic dynamics could play in enab…

Continual Learning