Learn, hack!

URL

http://dewy.fem.tu-ilmenau.de/CCC/22C3/audio/mp3/22C3-544-en-applied_machine_learning.mp3

File name

22C3-544-en-applied_machine_learning.mp3

File size

22.3 MB

MD5

fc9b047db040dbc7eaf4e8e097a89008

SHA1

2023e314641ae2793ae3f3cd861aa2224a34e160

Overview of the current state of research in Machine Learning including the general motivation, setup of learning problems, state-of-the-art learning algorithms and applications like our brain computer interface. The talk is going to have three parts: (a) What is Machine Learning about? This includes the general motivation (spam detection as example) and the setup of supervised learning problems. (b) What are state-of-the-art learning techniques? With a minimal amount of theory, I'll describe some methods including a currently very successful and easily applicable method called Support Vector Machines. I'll provide references to packaged implementations of these algorithms. (c) I'll discuss a few applications in greater detail, to show how Machine Learning can be successfully applied in practice. These will include: Handwritten letter/digit recognition, drug discovery, file classification (e.g. on Linux and BSD sourcecode), gene finding and brain-computer interfacing. I present the material as self-contained as possible. Part b will contain some math, but this will be kept to a minimum: I mainly want to bring ideas across.