论文标题
CNT（嘈杂目标的条件）：一种用于利用自上而下反馈的新算法
CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback
论文作者
论文摘要
我们提出了一个新的监督学习规则，称为噪声目标（CNT）的调节。这种方法在于根据随机噪声级别（从小到大噪声）（从小到大噪声）以嘈杂的目标（例如，模仿学习或分类中的标签中的行为）来调节模型。在推理时，由于我们不知道目标，因此我们只能以噪声代替噪声目标来运行网络。 CNT通过嘈杂的标签提供提示（噪声较小，我们可以更容易地推断出真实的目标）。这给出了两个主要好处：1）自上而下的反馈使该模型可以专注于更简单，更易消化的子问题和2）2）而不是学习从头开始解决任务，而是首先学习掌握简单的示例（噪音更少），同时缓慢地朝着更艰难的示例（以更多的噪音）逐渐发展。
We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in classification) at a random noise level (from small to large noise). At inference time, since we do not know the target, we run the network with only noise in place of the noisy target. CNT provides hints through the noisy label (with less noise, we can more easily infer the true target). This give two main benefits: 1) the top-down feedback allows the model to focus on simpler and more digestible sub-problems and 2) rather than learning to solve the task from scratch, the model will first learn to master easy examples (with less noise), while slowly progressing toward harder examples (with more noise).
