本文介绍了深度多任务和元学习的概念，强调它们在处理新任务和利用先验经验进行快速学习中的作用。多任务学习通过条件任务描述符优化目标，面临负转移和过拟合的挑战。元学习则关注如何利用过去任务的数据适应新任务，提出了通用的算法框架。
Lecture 1 Introduction
- Why should we care about deep multi-task & meta-learning?
deep learning allows us to handle unstructured inputs(pixels, languages, sensor readings, etc.)
without hand-engineering features, with less domain knowledge
Large, diverse data ——>deep learning——>broad generalization（能够实现广泛的推广）
- What if you need to quickly learn something new?
about a new person, for a new task, about a new environment, etc.
few-shot learning（少镜头学习）
by leveraging prior experience（利用先验知识）
This is where elements of multi-task learning can come into play.
- What is a task?
- Infromal problem definitions
最低0.47元/天 解锁文章
54
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
