Too Long; Didn't Read
When I first came across DeepMind’s paper “<a href="https://arxiv.org/abs/1606.04474" target="_blank">Learning to learn by gradient descent by gradient descent</a>”, my reaction was “Wow, how on earth does that work?”. Unfortunately, my first read-through of the paper was not that illuminating, and looking at the <a href="https://github.com/deepmind/learning-to-learn" target="_blank">code</a> was quite daunting.