论文标题
MTL2L：情境意识到的神经优化器
MTL2L: A Context Aware Neural Optimiser
论文作者
论文摘要
学习学习（L2L）训练元学习者，以帮助学习特定于任务的基础学习者。以前，已经表明，元学习者可以学习更新学习者参数的直接规则。与手工制作的渐变方法相比，学到的神经优化者更新了学习者。但是，我们证明了以前的神经优化器仅限于更新一个指定数据集上的学习者。为了解决输入域的异质性，我们引入了多任务学习学习（MTL2L），这是一种上下文意识到的神经优化器，该神经优化器基于输入数据自我修改其优化规则。我们表明，MTL2L能够更新学习者在元测试阶段对未见输入域的数据进行分类。
Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner. Previously, it was shown that a meta-learner could learn the direct rules to update learner parameters; and that the learnt neural optimiser updated learners more rapidly than handcrafted gradient-descent methods. However, we demonstrate that previous neural optimisers were limited to update learners on one designated dataset. In order to address input-domain heterogeneity, we introduce Multi-Task Learning to Learn (MTL2L), a context aware neural optimiser which self-modifies its optimisation rules based on input data. We show that MTL2L is capable of updating learners to classify on data of an unseen input-domain at the meta-testing phase.
