paper-with-me

홈 › Papers

A study on the plasticity of neural networks

2021-05-31 · Tudor Berariu, Wojciech Czarnecki, Soham De, Jorg Bornschein, Samuel Smith, Razvan Pascanu, Claudia Clopath

One aim shared by multiple settings, such as continual learning or transfer learning, is to leverage previously acquired knowledge to converge faster on the current task. Usually this is done through fine-tuning, where an implicit assumption is that the network maintains its plasticity, meaning that the performance it can reach on any given task is not affected negatively by previously seen tasks. It has been observed recently that a pretrained model on data from the same distribution as the one it is fine-tuned on might not reach the same generalisation as a freshly initialised one. We build and extend this observation, providing a hypothesis for the mechanics behind it. We discuss the implication of losing plasticity for continual learning which heavily relies on optimising pretrained models.

📄 PDF Abstract BibTeX arXiv:2106.00042

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningTransfer Learning

Similar Papers 제목 키워드 기반

Paired associative stimulation demonstrates alterations in motor cortical synaptic plasticity in patients with hepatic encephalopathy

2022-05-05 · Petyo Nikolov, Thomas J. Baumgarten, Shady Safwat Hassan, Nur-Deniz Füllenbach 외

Objective: Hepatic encephalopathy (HE) is a potentially reversible brain dysfunction caused by liver failure. Altered synaptic plasticity is supposed to play a major role in the pathophysiology of HE. Here, we used paire…

H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks

2020-12-01 · NeurIPS 2020 12 · Thomas Limbacher, Robert Legenstein

The ability to base current computations on memories from the past is critical for many cognitive tasks such as story understanding. Hebbian-type synaptic plasticity is believed to underlie the retention of memories over…

Question Answering

Environmental variability and network structure determine the optimal plasticity mechanisms in embodied agents

2023-03-12 · Emmanouil Giannakakis, Sina Khajehabdollahi, Anna Levina

The evolutionary balance between innate and learned behaviors is highly intricate, and different organisms have found different solutions to this problem. We hypothesize that the emergence and exact form of learning beha…

Form

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

2023-06-19 · NeurIPS 2023 11

In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly in scenarios when data acquisition is costly and risky. In principle, off-policy RL algorithms can improve sample efficiency by allowin…

reinforcement-learningReinforcement Learning (RL)

An objective function for self-limiting neural plasticity rules

2015-05-15

Self-organization provides a framework for the study of systems in which complex patterns emerge from simple rules, without the guidance of external agents or fine tuning of parameters. Within this framework, one can for…