Over the last years machine learning has become a hot topic. This is no surprise as the state of the art has reached levels that started to gain a lot of attention in the media: Self-driving cars, winning to Go game against top professional players and social media platforms that recognize your face in most online pictures.
This presentation provides an overall picture of machine learning and does not require any previous knowledge in the field. Sit back, relax and learn more about the following topics:
Historical background
Key concepts
Demos: Outlier detection, handwritten digit recognition, sentiment classification
At the end some less well known examples/topics will help to illustrate the current state of the art and should provide some food for thought regarding the future directions of this domain.
The goal of the talk is to provide a basic understanding about the field that is not about hype but more about actually working with available open source libraries. The technologies/libraries used for the demos: Docker, Mallet (for sentiment classification), Netflix/Surus (for robust outlier detection) and Deeplearning4j (for handwritten digit recognition).
Matthias Zimmermann
