Differences

This shows you the differences between two versions of the page.

--- start [2020/11/26 06:25]
IIS Webadmin
+++ start [2022/05/14 06:25]
IIS Webadmin
@@ Line 11: / Line 11: @@
 ===== 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]].
-  * [[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><!--
@@ Line 29: / Line 32: @@
 ===== News =====
-<HTML><table><tr valign="top"><td>2020-11-19</td><td>Justus Piater gives an invited talk <i>Machine Learning in Robotics</i> at <a href="https://baiome.org/">bAIome PI Talk, Center for
+<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
-    Biomedical AI, University Medical Center Hamburg-Eppendorf</a>, online. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem1', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem1Abstract" style="display:none">Machine Learning increasingly equips robots with
+    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
-    learning capabilities and flexibility.  This will enable them to
+    task with our annoying chores? How would we teach the robot to
-    act purposefully in unstructured environments and to react to
+    perform these tasks? Can we build such robots by equipping them
-    unforeseen events.  People can teach them intuitively to perform
+    with artificial intelligence? We will discuss how human and
-    tasks instead of having to program them in painstaking ways.
+    machine learning differ and how this impacts what skills,
-    Robots can learn from experience and can improve their behavior
+    including for communication, our helper robot will be able to
-    over time.  In this talk I will give an overview of methods,
+    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
-    opportunities, and challenges of machine learning in
+    Machines</i> at <a href="https://www.philosophie.uni-konstanz.de/ag-mueller/online-workshop-on-agency-life-and-creativity/">Workshop
-    robotics.</blockquote></td></tr><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&amp;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&amp;idreunion=424">GdR
+    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
-    ISIS Réunion Apprentissage et Robotique</a>, online. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem3', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem3Abstract" style="display:none">Conditional Neural Movement Primitives (CNMP) constitute
+    finding explanations, improving technology, or solving novel
-    a novel framework for robot programming by demonstration based on
+    problems in everyday life. Even imitating other humans, e.g. while
-    Conditional Neural Processes (CNP).  Like Bayesian methods such as
+    learning a new skill, is creative in that the imitator has to
-    Gaussian Processes (GP), CNP learn how target distributions depend
+    infer the conceptual structure underlying the observed
-    on data, and can be conditioned on specific data points to infer
+    manifestation and to regenerate the latter from the former. In
-    new target distributions at test time.  Unlike GP that are
+    contrast, current AI-enabled agents are unable to generate and
-    expensive to train and scale poorly to high dimensions, CNP are
+    draw upon such conceptual structures. Their learning is mostly
-    neural networks and are trained by gradient descent.  CNMP
+    driven by statistics, and any ability to produce novelty is
-    leverage CNP to represent motion trajectories that can be
+    largely limited to trial and error. I will try to characterize
-    conditioned, at test time, on task paramters such as goal
+    this fundamental difference between learning in human and
-    locations, via points, and/or force readings.  Moreover, CNMP are
+    artificial agents, and will discuss possible technological
-    conditioned on sensor readings during execution, resulting in
+    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
-    robust, reactive behavior.  This talk will present an overview of
+    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
-    how CNMP work and how they can be used in various robot
+    Bedarfserweckung?</i> at <a href="https://medical-update-hall.com/veranstaltungen/">Medical
-    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
+    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 &amp; 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
-    „Primers for Predocs – Strategien für eine erfolgreiche
+    analytical methods and artificial intelligence are motivating
-    Promotion“</a>, Universität Heidelberg. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem6', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem6Abstract" style="display:none">Massive availability of data and computing power are
+    entire branches of science to raise new questions and to develop
-    promoting data-driven methods in all areas of science and
+    new approaches. This digital transformation requires progressive,
-    technology.  I will describe how the University of Innsbruck
+    interdisciplinary synergies between the computational sciences and
-    supports this via its new Digital Science Center, and will give a
+    all other scientific disciplines.  The Digital Science Center
-    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,
+    (DiSC) at the University of Innsbruck meets this challenge by
-    Herausforderungen</i> at 47. Tagung des Innsbrucker Kreises von MoraltheologInnen
+    integrating and promoting digitalisation of scientific research.
-    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
+    In this talk I will present some examples of interdisciplinary
-    Understand My Robot?</i> at <a href="http://www.trustrobots.eu/">TrustRobots Lecture series
+    research by DiSC staff researchers who are experts in specific
-    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
+    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
-    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('newsitem11', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem11Abstract" style="display:none">A fundamental task of sensory processing is to detect
+    and Open Lab on Field Robotics - Interdisciplinary aspects of
-    and integrate feature items to group them into perceptual units
+    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
-    segregating them from other objects and the background. A
+    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
-    framework is discussed which explains how perceptual grouping at
+    system, the long-elusive AI breakthrough is popularly proclaimed
-    early as well as higher-level cognitive stages may be implemented
+    to be just around the corner.  Most recent successes have been due
-    in cortex. Different grouping mechanisms are implemented which are
+    in large part to massive data and computation, in particular using
-    attuned to basic features and feature combinations and mainly
+    deep artificial neural networks.  But can artificial cognition
-    evaluated along the forward sweep of stimulus processing. However,
+    really be achieved just by further scaling up existing
-    due to limitations of local feature detection mechanisms and
+    machine-learning techniques?  I discuss examples of simple,
-    inherent ambiguities, top-down feedback is required to deliver
+    perceptual problems that are easily solved by humans but very
-    contextual information helping to disambiguate initial
+    difficult for today's machine learning methods.  These problems
-    measurements. Feedback of contextual information is demonstrated
+    reflect how humans conceptualize their world.  Their mastery is
-    to improve object recognition performance, stabilize learning of
+    thus likely to be an essential prerequisite for autonomous robots
-    object categories, and integrate multi-sensory representations.
+    to attain higher levels of cognitive abilities.  To get there, a
+    few core issues can be identified that should drive research in
-    The canonical principles of neural computation define a set of
+    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>
-    core operations to implement above-mentioned mechanisms of
-    perceptual and cognitive inference. These operations can be
-    mapped, in a simplified form, onto neuromorphic platforms to
-    emulate brain-like computation. It is demonstrated that an
-    architecture composed of canonical circuit mechanisms can be
-    mapped onto neuromorphic chip technology facilitating low-energy
-    non-von Neumann computation.</blockquote></td></tr></table></HTML>
 [[news|Older News]]

User Tools

Site Tools

Differences

Page Tools