@emtiyaz This course, and it's Open Educational Resources, brought to you by
Nathanael Bosch, Julia Grosse, Agustinus Kristiadi, Marvin Pförtner, Jonathan Schmidt, Frank Schneider, Lukas Tatzel, Jonathan Wenger, and yours truly.

-- The End (of Term) --

@emtiyaz At the end, I sneak myself on stage on final time to summarize: https://youtu.be/t2CSqdfmKGA

Long story short:

Computation is inference. Whether information is loaded from disk or prepared directly on the GPU is not a fundamental distinction. If we quantify uncertainty everywhere, we can actively control, guide, manage and monitor the use of empirical as well as computational data.

People like @emtiyaz, Alex Immer, Erik Daxberger, Matthias Bauer, Runa Eschenhagen and Agustinus himself have built a beautifully comprehensive framework to turn deep models approximately into Gaussian processes, and thus transfer all the clean mechanisms associated with GPs to deep learning:

Calibrated, learnable uncertainty; out-of-distribution robustness; architecture-optimization by evidence maximization; multi-task, life-long learning, and the list goes on.

Frank Schneider started the round with a lecture on deep training. He argues that deep learning is only superficially an optimization problem in the strict sense. And that it is a poorly understood problem, despite its enormous emerging economic value.

```
https://youtu.be/PBcVZ5jEE5k
```

Thankfully, there are many leads to a new kind of training; and they are fundamentally probabilistic in nature. The strong stochasticity of mini-batch training should be embraced rather than ignored.