Persönlicher Status und Werkzeuge

Home Teaching Winter Semester 2013/14 Current Trends in Machine Learning

Current Trends in Machine Learning

WS 2013/14, TU München

Seminar

Location: Room 00.12.19 (new room!)
Date: Wednesday, First meeting 30.10.2013, Presentations starting on 08.01.2014
Time: 14:00 - 16:00
Lecturer: Rudolph Triebel, Jürgen Sturm, Jan Stühmer, Christian Kerl
ECTS: 4
SWS: 2

The course will be held in English. The students can do their presentation in German, but English is preferred.

Inhalt

Maschinelles Lernen bezeichnet Methoden um Muster unter Nutzung von Vorwissen in strukturierten Daten aufzufinden. In diesem Seminar werden aktuelle Themen anhand von Konferenzbeiträgen aus dem Bereich Maschinelles Lernen behandelt. Dazu gehören Anwendungen in der Robotik, der Signalverarbeitung (z. B. blinde Quellentrennung), Empfehlungsdienste (Recommender Systems) und sich zeitlich verändernde Daten. Jeder Student wählt eine wissenschaftliche Veröffentlichung, die er im Seminar präsentiert.

Teilnehmerzahl: 12 Studenten (Master).
Registrierung: per e-Mail an Rudolph Triebel und unter TUM online.

Description Machine Learning studies computational methods that find patterns in structured data. In this seminar we will discuss current trends in machine learning based on research articles, including applications in robotics, signal processing (e.g. blind source separation), recommender systems and time varying data. Every student picks a recent research paper on machine learning that he presents in the seminar.

Attendance is limited to 12 students (Master).
Registration: send email to Rudolph Triebel and on TUM online.

Important Dates
First Meeting Room 02.09.023, 14:00 - 16:00 30.10.2013 - fixed assignment of topic and date slides
SeminarRoom 00.12.19, 14:00 - 16:00 15.01.2014, 22.01.2014, 29.01.2014
Final Report28.02.2014


LaTeX-Template for the Report

A LaTeX-template for your seminar report is available for download here.

Paper Assigments
PaperSupervisorStudentPresentation date
What makes Paris look like Paris?Jürgen SturmLaszlo Habon15.01.2014
Leafsnap: A Computer Vision System for Automatic Plant Species IdentificationJürgen SturmShiv Baishya22.01.2014
Active Learning for Level Set EstimationJürgen SturmAynur Pashayeva29.01.2014
ImageNet Classification with Deep Convolutional Neural NetworksChristian KerlJohannes Mikulasch15.01.2014
Fast, Accurate Detection of 100,000 Object Classes on a Single MachineChristian KerlJunjie Bai22.01.2014
Multipath Sparse Coding Using Hierarchical Matching PursuitChristian KerlBurcu Karadeniz29.01.2014
Decision Tree Fields Rudolph Triebel Yahui Feng 15.01.2014
An Online Boosting Algorithm with Theoretical Justifications Rudolph Triebel Shoubhik Debnath22.01.2014
Active Learning for Large Multi-class Problems Rudolph Triebel Ioannis Chiotellis29.01.2014
A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles Jan StühmerAmin Abouee Mehrizi15.01.2014
How To Grade a Test Without Knowing the Answers - A Bayesian Graphical Model for Adaptive Crowdsourcing and Aptitude TestingJan StühmerRoc Reguant Comellas22.01.2014
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials Jan Stühmer Not assigned yet
Last edited 28.01.2014 14:35 by sturmju