RUG::B

Deep convolutional networks, overfitting, RBF kernels, GANs, nonlinear transformations, stochastic gradient descent, and of course the coming singularity and super intelligence. Machine learning buzzwords are all the rage now, but what does it mean for a machine to actually learn? What separates a machine that learns something from one that is merely programmed? And how does machine learning relate to human learning?

In this talk, I want to present a condensed and intuitive introduction to the most basic ideas behind machine learning. I will start at the point that is usually assumed as a prerequisite in technical text books and courses on the topic, allowing you to get the intuition behind the matrix multiplications and gradient descent algorithms that they commonly start with.

Learning can be interpreted as being able to deal with new situations based on past experience. In my talk, I will cover what happens during learning, how we can represent experience and learnings in a machine-friendly way, what elements are necessary for a complete ML system and explain different basic types of machine learning approaches.

Do's and don'ts when you move from a monolith to microservices.

I will describe the experience of being wrapping up a bunch of microservices under a single API.

What, and how to test when you are 100% using microservices.

And how to keep the microservices mindset consistent.

How we turned a test suite running for ~75-90' with random failures into a stable one running in ~10' by parallelizing tests for faster feedback and tracking and fixing random failures.