start
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
|
start [2020/11/23 08:52] IIS Webadmin |
start [2022/05/14 06:25] IIS Webadmin |
||
|---|---|---|---|
| Line 11: | Line 11: | ||
| ===== Working With Us ===== | ===== Working With Us ===== | ||
| + | * We are hiring [[jobs|two doctoral students]] in machine learning for computer vision or robotics. | ||
| * Check our thesis topics for [[theses/start|Bachelor and Master students]]. | * Check our thesis topics for [[theses/start|Bachelor and Master students]]. | ||
| - | * [[https://ellis.eu/|ELLIS]] PhD Program: [[https://ellis.eu/de/news/ellis-phd-program-call-for-applications|Call for Applications]] | + | <html><!-- |
| + | * [[https://ellis.eu/|ELLIS]] PhD Program: [[https://ellis.eu/news/ellis-phd-program-call-for-applications-deadline-november-15-2021|Call for Applications]] | ||
| + | --></html> | ||
| <html><!-- | <html><!-- | ||
| Line 29: | Line 32: | ||
| ===== News ===== | ===== News ===== | ||
| - | <HTML><table><tr valign="top"><td>2020-11-20</td><td>Simon Haller-Seeber and Patrick Lamprecht present a show <i>Explainable AI: A sneak peek into the Black-Box</i> at <a href="https://youtube.com/watch?v=4NVfPwdLnCg&t=17m43s">Science Slam</a>, online.</td></tr><tr valign="top"><td>2020-06-22</td><td>Justus Piater gives an invited talk <i>Conditional Neural Movement Primitives</i> at <a href="http://www.gdr-isis.fr/index.php?page=reunion&idreunion=424">GdR | + | <HTML><table><tr valign="top"><td>2022-05-11</td><td>Justus Piater gives an invited talk <i>Robots That Learn Like Humans?</i> at <a href="https://pintofscience.at/events/innsbruck">Pint of |
| - | ISIS Réunion Apprentissage et Robotique</a>, online. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem1', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem1Abstract" style="display:none">Conditional Neural Movement Primitives (CNMP) constitute | + | Science</a>, Innsbruck. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem0', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem0Abstract" style="display:none">Wouldn't it be great to have a helper robot that we can |
| - | a novel framework for robot programming by demonstration based on | + | task with our annoying chores? How would we teach the robot to |
| - | Conditional Neural Processes (CNP). Like Bayesian methods such as | + | perform these tasks? Can we build such robots by equipping them |
| - | Gaussian Processes (GP), CNP learn how target distributions depend | + | with artificial intelligence? We will discuss how human and |
| - | on data, and can be conditioned on specific data points to infer | + | machine learning differ and how this impacts what skills, |
| - | new target distributions at test time. Unlike GP that are | + | including for communication, our helper robot will be able to |
| - | expensive to train and scale poorly to high dimensions, CNP are | + | learn.</blockquote></td></tr><tr valign="top"><td>2022-02-19</td><td>Justus Piater gives an invited talk <i>Learning as a Creative Process in Humans and |
| - | neural networks and are trained by gradient descent. CNMP | + | Machines</i> at <a href="https://www.philosophie.uni-konstanz.de/ag-mueller/online-workshop-on-agency-life-and-creativity/">Workshop |
| - | leverage CNP to represent motion trajectories that can be | + | on “Agency, Life, and Creativity”</a>, online. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem1', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem1Abstract" style="display:none">Humans constantly engage in creative activity such as |
| - | conditioned, at test time, on task paramters such as goal | + | finding explanations, improving technology, or solving novel |
| - | locations, via points, and/or force readings. Moreover, CNMP are | + | problems in everyday life. Even imitating other humans, e.g. while |
| - | conditioned on sensor readings during execution, resulting in | + | learning a new skill, is creative in that the imitator has to |
| - | robust, reactive behavior. This talk will present an overview of | + | infer the conceptual structure underlying the observed |
| - | how CNMP work and how they can be used in various robot | + | manifestation and to regenerate the latter from the former. In |
| - | applications.</blockquote></td></tr><tr valign="top"><td>2020-06-03</td><td>Justus Piater appears in the media: Wie der Roboter denken lernt.</td></tr><tr valign="top"><td>2020-01-29</td><td>Justus Piater gives an invited talk <i>Digital Science</i> at <a href="https://www.graduateacademy.uni-heidelberg.de/karriere/veranstaltungsreihen.html">Vortragsreihe | + | contrast, current AI-enabled agents are unable to generate and |
| - | „Primers for Predocs – Strategien für eine erfolgreiche | + | draw upon such conceptual structures. Their learning is mostly |
| - | Promotion“</a>, Universität Heidelberg. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem4', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem4Abstract" style="display:none">Massive availability of data and computing power are | + | driven by statistics, and any ability to produce novelty is |
| - | promoting data-driven methods in all areas of science and | + | largely limited to trial and error. I will try to characterize |
| - | technology. I will describe how the University of Innsbruck | + | this fundamental difference between learning in human and |
| - | supports this via its new Digital Science Center, and will give a | + | artificial agents, and will discuss possible technological |
| - | flavor of machine learning for data analysis.</blockquote></td></tr><tr valign="top"><td>2020-01-20</td><td>Joanna Chimiak-Opoka, Carina König, and Justus Piater appear in the media: <a href="https://www.uibk.ac.at/newsroom/ergaenzung-digital-science-erfolgreich-gestartet.html.de">Ergänzung Digital Science erfolgreich gestartet – UIBK Newsroom</a>.</td></tr><tr valign="top"><td>2020-01-03</td><td>Justus Piater gives an invited talk <i>Künstliche Intelligenz: Grundlagen, Erfolge, | + | approaches that might help close this gap.</blockquote></td></tr><tr valign="top"><td>2021-11-24</td><td>Justus Piater is a panelist at a public discussion on <a href="https://www.linkedin.com/posts/elsa-innsbruck_letzte-woche-fand-zum-elsa-day-am-24112021-activity-6871397038093869057-16-7">Privacy |
| - | Herausforderungen</i> at 47. Tagung des Innsbrucker Kreises von MoraltheologInnen | + | in the Digital Age</a>, online. (Organized by ELSA Innsbruck)</td></tr><tr valign="top"><td>2021-10-22</td><td>Justus Piater gives an invited talk <i>Robotik und KI in der Medizin – nur |
| - | und SozialethikerInnen, Innsbruck.</td></tr><tr valign="top"><td>2019-12-19</td><td>Justus Piater appears in the media: <a href="https://tvthek.orf.at/profile/Tirol-heute/70023/Tirol-heute/14035670/Alexa-Siri-Co-Spione-im-eigenen-Haus/14610743">TV interview by ORF 2 Tirol Heute RedHaus (in German)</a>.</td></tr><tr valign="top"><td>2019-12-12</td><td>Justus Piater gives an invited lecture <i>Too Smart to Be Trusted – Do I Even Want to | + | Bedarfserweckung?</i> at <a href="https://medical-update-hall.com/veranstaltungen/">Medical |
| - | Understand My Robot?</i> at <a href="http://www.trustrobots.eu/">TrustRobots Lecture series | + | Update Hall 2021 – Fit für das neue Jahrzehnt</a>, UMIT, Hall in Tirol.</td></tr><tr valign="top"><td>2021-08-26</td><td>Justus Piater contributes a talk <i>Digital Science at the University of Innsbruck</i> at Aurora Research Conference Digital Society & Global Citizenship, Vrije Universiteit Amsterdam. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem4', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem4Abstract" style="display:none">Growing data processing capacities and progress in |
| - | Trust in Robots</a>, TU Vienna.</td></tr><tr valign="top"><td>2019-12-05</td><td>IIS guest <span style="font-weight:bold">Heiko Neumann</span>, University of Ulm, gives an invited colloquium <i>Biologically inspired visual-auditory processing – from | + | analytical methods and artificial intelligence are motivating |
| - | brain-like computation to neuromorphic algorithms</i> at <a href="https://www.uibk.ac.at/informatik/forschung/lunchtime-seminar/index.html.en">IFI Lunchtime Seminar</a>. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem9', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem9Abstract" style="display:none">A fundamental task of sensory processing is to detect | + | entire branches of science to raise new questions and to develop |
| - | and integrate feature items to group them into perceptual units | + | new approaches. This digital transformation requires progressive, |
| - | segregating them from other objects and the background. A | + | interdisciplinary synergies between the computational sciences and |
| - | framework is discussed which explains how perceptual grouping at | + | all other scientific disciplines. The Digital Science Center |
| - | early as well as higher-level cognitive stages may be implemented | + | (DiSC) at the University of Innsbruck meets this challenge by |
| - | in cortex. Different grouping mechanisms are implemented which are | + | integrating and promoting digitalisation of scientific research. |
| - | attuned to basic features and feature combinations and mainly | + | In this talk I will present some examples of interdisciplinary |
| - | evaluated along the forward sweep of stimulus processing. However, | + | research by DiSC staff researchers who are experts in specific |
| - | due to limitations of local feature detection mechanisms and | + | aspects of digital science.</blockquote></td></tr><tr valign="top"><td>2021-08-24</td><td>Justus Piater contributes a lecture <i>Picking and Placing</i> at <a href="https://www.uibk.ac.at/informatik/forschung/gmar-robotics-school-2021.html">2021 GMAR Summer School</a>, Villa Blanka, Innsbruck.</td></tr><tr valign="top"><td>2021-07-01</td><td>Justus Piater and Matteo Saveriano give an invited talk <i>Making Robots Learn to Perceive and Act with Understanding</i> at <a href="https://webservices.scientificnet.org/rest/entries/api/v1/blobs/200894">Workshop |
| - | inherent ambiguities, top-down feedback is required to deliver | + | and Open Lab on Field Robotics - Interdisciplinary aspects of |
| - | contextual information helping to disambiguate initial | + | robotics and its applications in outdoor scenarios</a>, NOI Techpark, Bolzano, Italy.</td></tr><tr valign="top"><td>2021-05-26</td><td>Justus Piater contributes a talk <i>Intelligente und interaktive Systeme</i> at <a href="http://www.gmar.at/aktuell/">GMAR Robotics Science |
| - | measurements. Feedback of contextual information is demonstrated | + | Talks</a>, online.</td></tr><tr valign="top"><td>2021-03-24</td><td>Justus Piater gives an invited lecture <i>Machine Learning, Perception, And Abstract Concepts</i> at Invited lecture at Ontario Tech U, Canada, online. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem8', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem8Abstract" style="display:none">With every spectacular achievement of a machine learning |
| - | to improve object recognition performance, stabilize learning of | + | system, the long-elusive AI breakthrough is popularly proclaimed |
| - | object categories, and integrate multi-sensory representations. | + | to be just around the corner. Most recent successes have been due |
| - | + | in large part to massive data and computation, in particular using | |
| - | The canonical principles of neural computation define a set of | + | deep artificial neural networks. But can artificial cognition |
| - | core operations to implement above-mentioned mechanisms of | + | really be achieved just by further scaling up existing |
| - | perceptual and cognitive inference. These operations can be | + | machine-learning techniques? I discuss examples of simple, |
| - | mapped, in a simplified form, onto neuromorphic platforms to | + | perceptual problems that are easily solved by humans but very |
| - | emulate brain-like computation. It is demonstrated that an | + | difficult for today's machine learning methods. These problems |
| - | architecture composed of canonical circuit mechanisms can be | + | reflect how humans conceptualize their world. Their mastery is |
| - | mapped onto neuromorphic chip technology facilitating low-energy | + | thus likely to be an essential prerequisite for autonomous robots |
| - | non-von Neumann computation.</blockquote></td></tr><tr valign="top"><td>2019-11-26</td><td>IIS guest <span style="font-weight:bold">Tamim Asfour</span>, Karlsruhe Institute of Technology, gives an invited keynote <i>Engineering Humanoids with Motion Intelligence</i> at <a href="https://www.uibk.ac.at/informatik/studium/inday-students/index.html.en">inday students</a>. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem10', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem10Abstract" style="display:none">Humanoid robotics plays a central role in robotics | + | to attain higher levels of cognitive abilities. To get there, a |
| - | research as well as in understanding intelligence. Engineering | + | few core issues can be identified that should drive research in |
| - | humanoid robots that are able to learn from humans and | + | cognitive robotics.</blockquote></td></tr><tr valign="top"><td>2021-01-28</td><td>Matteo Saveriano gives an invited talk <i>Making robots to learn from human observation?</i> at <a href="https://www.bmeia.gv.at/en/austrian-embassy-ottawa/news/events/detail/article/showcasing-young-austrian-scholars-and-scientists-an-original-seven-part-virtual-lectures-ser/">Showcasing Young Austrian Scholars and Scientists, Austrian cultural forum, Ottawa</a>, online.</td></tr></table></HTML> |
| - | sensorimotor experience, to predict the consequences of actions | + | |
| - | and exploit the interaction with the world to extend their | + | |
| - | cognitive horizon remains a research grand challenge. Currently, | + | |
| - | we are experiencing AI systems with superhuman performance in | + | |
| - | games, image and speech processing. However, the generation of | + | |
| - | robot behaviors with human-like motion intelligence and | + | |
| - | performance has yet to be achieved. In this talk, I will present | + | |
| - | recent progress towards engineering 24/7 humanoid robots that link | + | |
| - | perception and action to generate intelligent behavior. I will | + | |
| - | show the ARMAR humanoid robots performing complex grasping and | + | |
| - | manipulation tasks in kitchen and industrial environments, | + | |
| - | learning actions from human observation and experience as well as | + | |
| - | reasoning about object-action relations.</blockquote></td></tr></table></HTML> | + | |
| [[news|Older News]] | [[news|Older News]] | ||
start.txt · Last modified: 2024/04/09 13:00 by Justus Piater