22 May, 2018
During this meetup there will be two talks
Talk 1: What if… we can predict the Bitcoin Market?
This meetup will tell the story about how a crazy idea rapidly evolves and what we learned from it. It is about bitcoins. A data scientist and a software nerd joined forces in a bold quest to come up with an algorithm to predict the bitcoin market. The reasoning was simple and somewhat naive: ”we are likely to fail, but at least we learned all the cool stuff”. During this talk we will elaborate on our approach, our successes and our mistakes. Did they succeed? Well, come and see this talk!
We will use deep learning methods in Tensorflow. In our talk we present the different aspects of a deep learning model such as activation functions, gradient descent and backpropagation. The influence of these aspects will be shown and finally the performance of such a complex model will be compared to a much easier model as logistic regression. Is it worth to use all these hidden layers and difficult techniques? Or is it just fun and does a logistic regression model perform just as well.
Microservices development is common practice for quite some time at the Cloud, Big data and Internet department of the Dutch National Police. But about a year ago we saw areas where we could improve.
At the time all the microservices were running on VM’s that were purpose-built for each particular microservice. There was ad-hoc automation around creating these VM’s. Furthermore each microservice was deployed on a single instance and thus not high available (HA). We set out to change this, because we want 24/7 availability, zero-downtime deployments, high scalability, and a more self-service infrastructure.
In this talk we will show you how we gradually migrated our dozens of microservices to a high available cloud-native container platform. The key here is ‘gradual migration’. We wanted to move fast but avoid a big bang change on both the technology and process side.
With the help of Hashicorp’s Terraform, Consul and Nomad plus a few in-house developed components (in Go, Java and Typescript) we managed to address our concerns. You will leave this talk with an understanding how these tools provide value when used on their own, and when composed together.
17:30 Walk in
18:30 talk 1
19:30 talk 2
20:15 Drinks, Q&A
Olaf de Leeuw
As a graduated Mathematician in stochastic processes I’m highly interested in the advanced theoretics of Neural Networks and other Machine Learning models. With my knowledge I want to improve the models I make and not only apply the several Machine Learning packages available in programming languages. On the other hand I have a short history of two years in teaching Mathematics at a high school to mostly uninterested kids and therefore I’m experienced in explaining difficult matter very clearly and I’m keen on keeping things simple and useful as possible.
works as Full Stack Data Engineer at DataWorkz. He focuses on creating big data systems where simplicity is the key and can be very passionate about it! He also likes to help others and share knowledge