神经混合密度过程
Neural Mixture Density Processes
NMDP 通过混合密度建模和 EM 训练构建函数先验，其任务特定参数更新机制可用于视觉少样本任务（如少样本分类、分割）的快速自适应，减少过拟合。
原文依据 The NMDP decomposes model parameters into task-agnostic and task-specific components to represent function distributions more flexibly.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论神经过程（NP）是一种概率元学习模型，通过全局潜变量学习函数分布。它利用过去的经验，在少样本场景中实现快速适应。然而，NP 中潜变量结构和条件机制的设计仍未得到充分探索，尽管它们对于捕获多样化的函数分布至关重要。本文通过混合密度建模提出了一种新的 NP 变体，称为神经混合密度过程（NMDP）。NMDP 将模型参数分解为任务无关和任务特定的组件，以更灵活地表示函数分布。我们通过期望最大化算法训练模型，以构建表达性强的函数先验。与现有工作相比，我们的方法保持了若干优势：（i）通过更新网络参数的一小部分来减少过拟合，（ii）通过单纯形中的分布获得紧凑的任务表示，（iii）生成似然在迭代中具有改进保证。实验结果表明，我们的方法能够达到有竞争力的性能并具备足够的可解释性。
英文原文摘要 1149 字符
The neural process (NP) is a probabilistic meta learning model that learns distributions over functions via a global latent variable.It enables fast adaptation in few-shot scenarios by leveraging past experience. However, the design of latent variable structures and conditioning mechanisms in NPs remains underexplored, despite their importance in capturing diverse functional distributions.This paper proposes a new variant of NPs via mixture density modeling, referred to as the neural mixture density process (NMDP).The NMDP decomposes model parameters into task-agnostic and task-specific components to represent function distributions more flexibly. We train the model via the Expectation-Maximization algorithm to construct expressive functional priors.Compared with existing work, our method maintains several advantages: (i) less overfitting by updating a small part of the network parameters, (ii) compact task representation via distributions in the simplex,(iii) an improvement guarantee of generative likelihoods over iteration. Experimental results show that our method can achieve competitive performance with adequate explainability.