All of the below papers are free to access and cover a range of topics from Hypergradients to modeling yield response for CNNs. Each expert also included a reason as to why the paper was picked as well as a short bio. We spoke to Jeff back in January, and at that time, he couldn't pick just one paper as a must-read, so we let him pick two. This paper unpacks two key talking points, the limitations of sparse training data, and also if recurrent networks can support meta-learning in a fully supervised context. These points are addressed in seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.

I would recommend starting your GAN journey with the DCGAN paper. This paper shows how convolutional layers can be used with GANs and provides a series of additional architectural guidelines for doing this. The paper also discusses topics such as Visualizing GAN features, Latent space interpolation, using discriminator features to train classifiers, and evaluating results. All of these additional topics are bound to come up in your GAN research. In summation, the DCGAN paper is a must-read GAN paper because it defines the architecture in such a clear way that it is easy to get started with some code and begin developing an intuition for GANs.

The answer to this question will become a huge bibliography that nobody looks at eventually. I think you should start reading some basic book about the topic and go specif from there. However, I will refer to this paper that actually kills all other papers:-) http://teamcore.usc.edu/WeeklySe... - Machine Learning That Matters, Kiri L. Wagstaff