×
Abstract. Meta-learning models learn to generalise to unseen tasks at test time. We introduce a meta-learning algorithm which balances (global) ...
We propose probabilistic task modelling – a gen- erative probabilistic model for collections of tasks used in meta-learning. The proposed model com-.
Jun 9, 2021 · Abstract:We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning.
Missing: Adaptation | Show results with:Adaptation
Mar 24, 2024 · We propose an Adaptive Meta-Learning Probabilistic Inference Framework (AMPIF) based on sequence decomposition, which can effectively enhance the long sequence ...
Dec 3, 2020 · PAML is a probabilistic formulation of active meta-learning. By exploiting learned task representations and their relationship in latent space, PAML can use ...
Jul 17, 2020 · We provide empirical evidence that our approach improves data-efficiency when compared to strong baselines on simulated robotic experiments.
In this paper, we propose a probabilistic meta-learning algorithm that can sample models for a new task from a model distribution.
People also ask
This paper proposes an Adaptive Meta-Learning Probabilistic. Inference Framework (AMPIF) for long sequence prediction. This can address the potential domain ...
Our main contribution is a probabilistic active meta-learning (PAML) algorithm that improves data- efficiency by selecting which tasks to learn next based on ...
Missing: Adaptation | Show results with:Adaptation
We summarize the recent progress made by probabilistic programming as a uni- fying formalism for the probabilistic, symbolic, and data-driven aspects of ...