Züri ML #24: Deep Learning for Go, and Scikit-Learn

Dies ist ein vergangenes Event

229 Personen haben teilgenommen

Details

confirmed schedule:

• AlphaGo from a Go Player and an AI perspective
Thomas Koller (https://www.hslu.ch/de-ch/hochschule-luzern/ueber-uns/personensuche/profile/?pid=666), HSLU

• Robust and Calibrated Estimators with Scikit-Learn
Gilles Louppe (https://glouppe.github.io/), core contributor to scikit-learn, NYU and CERN

Abstracts:

• AlphaGo from a Go Player and an AI perspective

The computer program AlphaGo from Google DeepMind has recently defeated one of the strongest Go players, Lee Sedol, to the astonishment of both the go and the AI community. In the talk, we will have a look at the concepts and goals in the game of go and why it was believed to be such a hard problem to solve. We will discuss AlphaGo’s approach and how it differentiates from previous attempts and finally look at some exciting moments in the games. Does AlphaGo play like a human? Does it make mistakes? Can we learn from the computer? Does it understand go concepts? A look at the reactions from the go community and an outlook on the future of AlphaGo rounds up the talk.
Prof. Dr. Thomas Koller is lecturer and researcher in computer science with special focus on image processing, computer graphics and web development. He has worked on 3D image processing and computer graphics applications at the interdisciplinary project center for supercomputing at the ETH, in the computer graphics lab at EPFL and at the computer vision lab at ETH before joining a startup company as head of development. He then worked as software consultant, project manager and senior trainer at Zühlke AG before coming to HSLU, where he is currently involved in several projects in the area of computer vision and machine learning. He has been playing Go for more than 20 years and is currently president of the Zurich Go club.

• Robust and Calibrated Estimators with Scikit-Learn

Scikit-learn has become the go-to library for machine learning and data analysis tasks. It leverages the breadth of the Python programming language for math, science, and statistics, by building on top of several existing Python packages - NumPy, SciPy, and matplotlib. The resulting libraries can be used either for interactive “workbench” applications or be embedded into other software and reused. The kit is available under a BSD license, so it’s fully open and reusable.

This presentation will use the interactive python notebook
"Robust and calibrated estimators with Scikit-Learn" which you can find here:
https://github.com/glouppe/tutorial-scikit-learn

Networking Apero - Drinks sponsored by

SGAICO (http://www.s-i.ch/sgaico/) - AI in Switzerland