trivago academy at InVision: Machine Learning 2.0 with Xander Steenbrugge
Xander Steenbrugge is a passionate engineer fascinated by Machine Learning and Artificial Intelligence, public speaker and YouTube vlogger at ‘Arxiv Insights’. Through his thesis on brain-computer interfaces at Ugent, he first came into contact with the vast opportunities provided by data driven computer algorithms. After his Master of Science in electrical engineering, he also took an extra masters degree in business economics.
As a Machine Learning consultant he has worked on many different projects including computer vision (object tracking, optical character recognition, image classification, ..), natural language processing (chatbots, text classification, …) and many others using mostly open source tools like TensorFlow and Pytorch in combination with compute resources on the Google cloud platform.
Lately he started focussing on the interface between academic research and the real world through a PhD in Deep Reinforcement Learning focussed on applying these novel algorithms to industrial process optimization. He is now head of applied ML-research at ML6.
Xander will talk about:
Machine Learning 2.0, a glimpse on the near future of intelligent system design
Over the past 5 years Machine Learning techniques have dramatically reshaped the landscape of traditional, rule based software. This trend emerged out of decades of academic research but is now rapidly finding its way to an ever increasing number of businesses.
And yet, most of the ML systems in use today are what we could call “Static Inference Machines”: take input sample X, produce output Y and repeat. Standard examples of this framework include image classification, machine translation, music recommendation and many more. Additionally, almost all practical systems to date are trained with supervised learning, requiring large volumes of labelled training data: a major drawback in many practical settings.
As a response to these inherent restrictions, this talk will introduce some of the most exciting new paradigms in intelligent software design such as Generative Networks and Reinforcement Learning that enable systems to learn automatically from unlabeled data.
From a general overview of the problem setting to some fascinating practical examples, this talk will try to shed some light on the future of Machine Learning.
You will find parking spaces in the surrounding streets and car parks.