Stanford Class on Deep Multi-Task and Meta-Learning

The field of meta-learning is still very immature though. I can see why you would already want to start a scholarly discourse on the topic, but I am not sure how useful these techniques are for the students involved. They are still very ad hoc and often unprincipled.<p>This is a good article on the topic: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1902.03477" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1902.03477</a>

Asking as someone who does not work with AI but has taken a couple of courses in ML:<p>What new things will I be able to do after this course?<p>(in a practical sense, the technical description on the course page I can read myself)

Good to see Chelsea Finn end up at Stanford. I had breakfast with her and her parents in 2013 when she was an undergraduate at MIT and it was fun to hear what options she was thinking about for her career.<p>I took a look at the course outline, and except for AutoML, it appears to be a one stop shop for learning multi-task and meta-learning. I just bookmarked the lectures on youtube.

Humans observe an object once, such as a cup for drinking water, and we immediately grasp its &quot;cupness&quot;. We can identify infinite varieties of cups despite variations in morphology, design, utility and context. Simply based on a single learning instance. This absence of any neural theory of inference is at the crux of the problem ;)<p>Shortcut Learning in Deep Neural Networks<p><a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2004.07780" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2004.07780</a>

This looks super cool! Prof. Finn has been doing a lot of interesting research in RL and meta-learning for several years, it&#x27;s great to get a chance to learn this material directly from her.