Intelligent and Interactive Systems

User Tools

Site Tools


start

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
start [2020/05/13 20:44]
Justus Piater
start [2020/06/23 06:25] (current)
IIS Webadmin
Line 28: Line 28:
 ===== News ===== ===== News =====
  
-<​HTML><​table><​tr valign="​top"><​td>​2020-03-19</​td><​td>​Justus Piater gives an invited talk <i>Machine Learning in Robotics</i> at <a href="https://baiome.org/">bAIome PI Talk</​a>, ​Center for Biomedical AI at the University Medical Center +<​HTML><​table><​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 
-    Hamburg-Eppendorf. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem0',​ '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="​newsitem0Abstract"​ style="​display:​none">​Machine Learning increasingly equips robots with +    ISIS Réunion Apprentissage et Robotique</​a>, ​online. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem0',​ '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="​newsitem0Abstract"​ style="​display:​none">​Conditional Neural Movement Primitives (CNMP) constitute 
-    ​learning capabilities and flexibility.  ​This will enable them to +    ​a novel framework for robot programming by demonstration based on 
-    ​act purposefully in unstructured environments ​and to react to +    Conditional Neural Processes (CNP).  ​Like Bayesian methods such as 
-    ​unforeseen events.  ​People can teach them intuitively to perform +    ​Gaussian Processes (GP), CNP learn how target distributions depend 
-    ​tasks instead of having ​to program them in painstaking ways+    on data, and can be conditioned on specific data points ​to infer 
-    ​Robots ​can learn from experience and can improve their behavior +    ​new target distributions at test time.  ​Unlike GP that are 
-    ​over time.  ​In this talk will give an overview of methods, +    ​expensive ​to train and scale poorly to high dimensions, CNP are 
-    ​opportunities, ​and challenges of machine learning ​in +    neural networks and are trained by gradient descent CNMP 
-    ​robotics.</​blockquote></​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+    ​leverage CNP to represent motion trajectories that can be 
 +    ​conditioned,​ at test time, on task paramters such as goal 
 +    locations, via points, and/or force readings.  ​Moreover, CNMP are 
 +    conditioned on sensor readings during execution, resulting in 
 +    robust, reactive behavior. ​ This talk will present ​an overview of 
 +    ​how CNMP work and how they can be used in various robot 
 +    ​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
     „Primers for Predocs – Strategien für eine erfolgreiche     „Primers for Predocs – Strategien für eine erfolgreiche
-    Promotion“</​a>,​ Universität Heidelberg. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem2', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem2Abstract" style="​display:​none">​Massive availability of data and computing power are+    Promotion“</​a>,​ Universität Heidelberg. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem3', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem3Abstract" style="​display:​none">​Massive availability of data and computing power are
     promoting data-driven methods in all areas of science and     promoting data-driven methods in all areas of science and
     technology. ​ I will describe how the University of Innsbruck     technology. ​ I will describe how the University of Innsbruck
Line 48: Line 54:
     Understand My Robot?</​i>​ at <a href="​http://​www.trustrobots.eu/">​TrustRobots Lecture series     Understand My Robot?</​i>​ at <a href="​http://​www.trustrobots.eu/">​TrustRobots Lecture series
     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     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
-    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('​newsitem7', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem7Abstract" style="​display:​none">​A fundamental task of sensory processing is to detect+    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('​newsitem8', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem8Abstract" style="​display:​none">​A fundamental task of sensory processing is to detect
     and integrate feature items to group them into perceptual units     and integrate feature items to group them into perceptual units
     segregating them from other objects and the background. A     segregating them from other objects and the background. A
Line 70: Line 76:
     architecture composed of canonical circuit mechanisms can be     architecture composed of canonical circuit mechanisms can be
     mapped onto neuromorphic chip technology facilitating low-energy     mapped onto neuromorphic chip technology facilitating low-energy
-    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('​newsitem8', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem8Abstract" style="​display:​none">​Humanoid robotics plays a central role in robotics+    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('​newsitem9', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem9Abstract" style="​display:​none">​Humanoid robotics plays a central role in robotics
     research as well as in understanding intelligence. Engineering     research as well as in understanding intelligence. Engineering
     humanoid robots that are able to learn from humans and     humanoid robots that are able to learn from humans and
Line 86: Line 92:
     learning actions from human observation and experience as well as     learning actions from human observation and experience as well as
     reasoning about object-action relations.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2019-11-25</​td><​td>​Justus Piater gives an invited talk <​i>​Enabling Robots to Learn Abstract Concepts</​i>​ at <a href="​https://​tricolore.inf.unibz.it/​tricolore2019/​program/">​TriCoLore     reasoning about object-action relations.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2019-11-25</​td><​td>​Justus Piater gives an invited talk <​i>​Enabling Robots to Learn Abstract Concepts</​i>​ at <a href="​https://​tricolore.inf.unibz.it/​tricolore2019/​program/">​TriCoLore
-    – Creativity | Cognition | Computation</​a>,​ Bolzano, Italy.</​td></​tr><​tr valign="​top"><​td>​2019-11-18</​td><​td>​Justus Piater gives an invited talk <​i>​Künstliche Intelligenz in einer menschlichen +    – Creativity | Cognition | Computation</​a>,​ Bolzano, Italy.</​td></​tr></​table></​HTML>​
-    Gesellschaft</​i>​ at Robotik in Medizin und Pflege – Jubiläumssymposium +
-    des Klinischen Ethikkommittees,​ A.ö. Landeskrankenhaus – Universitätskliniken +
-    Innsbruck.</​td></​tr></​table></​HTML>​+
  
 [[news|Older News]] [[news|Older News]]
start.txt · Last modified: 2020/06/23 06:25 by IIS Webadmin