paper-with-me

홈 › Papers

Neuromodulated Meta-Learning

2024-11-11 · Jingyao Wang, Huijie Guo, Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Hui Xiong, Gang Hua

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the \emph{structure constraint} with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at \href{https://github.com/WangJingyao07/NeuronML}{https://github.com/WangJingyao07/NeuronML}.

📄 PDF Abstract BibTeX arXiv:2411.06746

Code (1)

wangjingyao07/neuronml 공식 구현 pytorch

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

2020-02-24 · ICLR 2019 5 · Thomas Miconi, Aditya Rawal, Jeff Clune, Kenneth O. Stanley

The impressive lifelong learning in animal brains is primarily enabled by plastic changes in synaptic connectivity. Importantly, these changes are not passive, but are actively controlled by neuromodulation, which is its…

Language ModelingLanguage ModellingLifelong learningreinforcement-learning+2

Context Meta-Reinforcement Learning via Neuromodulation

2021-10-30 · Eseoghene Ben-Iwhiwhu, Jeffery Dick, Nicholas A. Ketz, Praveen K. Pilly 외

Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments. Such a feat is achieved through dynamic representations in an agent's policy network (obt…

continuous-controlContinuous ControlMeta Reinforcement Learningreinforcement-learning+2

Learning to Continually Learn

2020-02-21 · Shawn Beaulieu, Lapo Frati, Thomas Miconi, Joel Lehman 외

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default te…

Continual LearningLifelong learningMeta-Learning

Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks

2020-05-22 · Samuel Schmidgall

The adaptive learning capabilities seen in biological neural networks are largely a product of the self-modifying behavior emerging from online plastic changes in synaptic connectivity. Current methods in Reinforcement L…

Meta-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Learning to learn online with neuromodulated synaptic plasticity in spiking neural networks

2022-06-25 · Samuel Schmidgall, Joe Hays

We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning. Although substantial progress has been made tow…

BIG-bench Machine Learning