WORKSHOP FORMAT
The workshop format wll be as usual: arrival on Sunday afternoon (September 25th), dinner will be served. Workshop ends on Wednesday September 28th after lunch.
DETAILED PROGRAM
The final program can be downloaded here
LINKS TO PRESENTATIONS
Following the links below you can download the slides for the oral presentations (see the final program for titles and full list of authors)
INVITED PLENARY TALKS
INVITED TUTORIAL/DISCUSSION TALKS
Marco Campi
REGULAR PRESENTATIONS
TRAIL RUNNING EARLY MORNING SESSIONS (NEW!)
For running enthusiasts, there are plenty of opportunities for trail running in the surroundings of the castle.
A map can be downloaded here and here.
For those really addicted, we are trying to organize a very early running session on Tuesday 27th, and get to the top of "Crodon del Gevero" (~850mt ascent from Castelbrando), stay tuned!
INSTRUCTIONS FOR POSTERS:
We recommend A0 format for the posters.
Authors will also present a "poster teaser" of about one minute right before the poster session as indicated in the program.
To this purpose authors should send ONE slide in pdf format to info.ernsi2016@dei.unipd.it by September 15th.
Please include in the message which poster session (A,B or C) your poster is scheduled for.
INVITED PLENARY SPEAKERS
The workshop will feature plenary lectures given by two invited speakers:
- Prof. Domenico Giannone (Federal Reserve Bank of New York)
Title: Now-Casting and the Real-Time Data Flow
Abstract: The term now-casting is a contraction for now and forecasting and has been used for a long time in meteorology and recently also in economics. In this chapter we survey recent developments in economic now-casting with special focus on those models that formalize key features of how market participants and policymakers read macroeconomic data releases in real-time, which involves monitoring many data, forming expectations about them and revising the assessment on the state of the economy whenever realizations diverge sizeably from those expectations.
- Prof. Jan Peters (Professor, Technische Universität Darmstadt;Research Group Leader, Max Planck Institute for Intelligent Systems)
Title: Machine Learning of Motor Skills for Robots: From Simple Skills to Table Tennis and Manipulation
Abstract: Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can learn tasks triggered by environmental context or higher level instruction. However, learning techniques have yet to live up to this promise as only few methods manage to scale to high-dimensional manipulator or humanoid robots. In this talk, we investigate a general framework suitable for learning motor skills in robotics which is based on the principles behind many analytical robotics approaches. It involves generating a representation of motor skills by parameterized motor primitive policies acting as building blocks of movement generation, and a learned task execution module that transforms these movements into motor commands. We discuss learning on three different levels of abstraction, i.e., learning for accurate control is needed to execute, learning of motor primitives is needed to acquire simple movements, and learning of the task-dependent „hyperparameters“ of these motor primitives allows learning complex tasks. We discuss task-appropriate learning approaches for imitation learning, model learning and reinforcement learning for robots with many degrees of freedom. Empirical evaluations on a several robot systems illustrate the effectiveness and applicability to learning control on an anthropomorphic robot arm. These robot motor skills range from toy examples (e.g., paddling a ball, ball-in-a-cup) to playing robot table tennis against a human being and manipulation of various objects.
SOCIAL PROGRAM (tuesday September 27th afternoon)
The social program will include a guided visit to the Castle as well as a visit to a local winery where we will visit the cellar, learn about how Prosecco is made and taste their wines.
