Session
Hauptprogramm 35C3
Science

Introduction to Deep Learning

This talk will teach you the fundamentals of machine learning and give you a sneak peek into the internals of the mystical black box. You'll see how crazy powerful neural networks can be and understand why they sometimes fail horribly.

Computers that are able to learn on their own. It might have sounded like science-fiction just a decade ago, but we're getting closer and closer with recent advancements in Deep Learning. Or are we?

In this talk, I'll explain the fundamentals of machine-learning in an understandable and entertaining way. I'll also introduce the basic concepts of deep learning. With the current hype of deep learning and giant tech companies spending billions on research, understanding how those methods works, knowing the challenges and limitations is key to seeing the facts behind the often exaggerated headlines.

One of the most common applications of deep learning is the interpretation of images, a field that has been transformed significantly in recent years. Applying neural networks to image data helps visualising and understanding many of the faults as well as advantages of machine learning in general. As a research scientist in the field of automated analysis of bio-medical image data, I can give you some insights into these as well as some real-world applications.

Additional information

Type lecture
Language English

More sessions

12/27/18
Science
Jost Migenda
Eliza
Neutrinos are “ghost-like” elementary particles that can literally go through walls. They can bring information from places that are impossible to observe through other means. This talk provides a glimpse behind the scenes of a next-generation neutrino detector called Hyper-Kamiokande – a cylindrical water tank the size of a high-rise building. I will describe some of the problems you encounter when planning a subterranean detector of this size, and explain how this detector helps us ...
12/27/18
Science
sven
Clarke
After launching a spacecraft into orbit the actual work for mission control starts. Besides taking care of the position and speed of the spacecraft this includes e.g. detailed modeling of the power usage, planning of ground station contacts, payload operations and dealing with unexpected anomalies. In this talk we will see many examples of problems particular to space crafts and how they influence the way space craft mission operations works.
12/27/18
Science
Jürgen Pahle
Eliza
How to apply Shannon's information theory to biology.
12/27/18
Science
Hannes Mehnert
Dijkstra
TCP/IP is the most widely used protocol on the Internet for transmitting data. But how does it work in detail? This talk will explain the TCP protocol, from handshake over established to teardown in detail - and elaborate a bit on protocol adjustments over time and congestion control.
12/27/18
Science
Borg
CRISPR/Cas hat die Genforschung revolutioniert und könnte bald in großem Stil gentechnisch eingesetzt werden. Aber was ist CRISPR und wie funktioniert es? Kurz gesagt: Teile des adaptiven Immunsystems von Bakterien werden genutzt, um Gene zu verändern. Und das funktioniert präziser als mit jedem anderen Werkzeug zuvor und offenbar in allen Tier- und Pflanzenarten. Damit ist CRISPR anders als die herkömmlichen Methoden der Gentechnik. Es ist einfach anzuwenden, preiswert, schnell, extrem ...
12/27/18
Science
sri
Clarke
An (almost) self-contained introduction to the basic ideas of quantum mechanics. The theory and important experimental results will be discussed.
12/27/18
Science
Theodor Sperlea
Dijkstra
As humans have a large negative impact on ecosystems all around the globe, we are approaching a major extinction event in which around 70% of all species will go extinct. This talk will give an introduction to a data-driven and system-based view of ecology.