Jacques Kaiser

Jacques Kaiser

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

PhD on Synaptic Learning for Neuromorphic Vision

12 minute read

Published:

After over five years of researching in the field of biological learning for robotics, I have successfully completed my PhD. The full dissertation is published on the KIT bibliothek. In this blog post, I introduce the field of neuromorphic computing in layman’s terms, and present some of the results.

ROS Tensorflow

4 minute read

Published:

In this blog post I go through some useful techniques to nicely integrate Tensorflow (TF) in ROS nodes. The related code can be found in the following ros_tensorflow github repo.

Gleeo time plotter

5 minute read

Published:

I have been using the Gleeo time tracker app on my phone to track my time at work for multiple years. To make sense of the data, I implemented a jupyter notebook. The notebook reports:

  • Total time spent per project
  • Time spent per project [per unit of time]
  • Over(under)hours aggregation, accounting for holidays

portfolio

publications

Retina Color-Opponency Based Pursuit Implemented Through Spiking Neural Networks in the Neurorobotics Platform

Published in In the proceedings of Conference on Biomimetic and Biohybrid Systems, 2016

Use Google Scholar for full citation

Recommended citation: Alessandro Ambrosano, Lorenzo Vannucci, Ugo Albanese, Murat Kirtay, Egidio Falotico, Georg Hinkel, Jacques Kaiser, Stefan Ulbrich, Paul Levi, Christian Morillas, Alois Knoll, Marc-Oliver Gewaltig, Cecilia Laschi, "Retina Color-Opponency Based Pursuit Implemented Through Spiking Neural Networks in the Neurorobotics Platform." In the proceedings of Conference on Biomimetic and Biohybrid Systems, 2016.

Towards a framework for end-to-end control of a simulated vehicle with spiking neural networks

Published in In the proceedings of International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), 2016

Use Google Scholar for full citation

Recommended citation: Jacques Kaiser, J Tieck, Christian Hubschneider, Peter Wolf, Michael Weber, Michael Hoff, Alexander Friedrich, Konrad Wojtasik, Arne Roennau, Ralf Kohlhaas, Rüdiger Dillmann, J. Zöllner, "Towards a framework for end-to-end control of a simulated vehicle with spiking neural networks." In the proceedings of International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), 2016.

Connecting Artificial Brains to Robots in a Comprehensive Simulation Framework: The Neurorobotics Platform

Published in Frontiers in Neurorobotics, 2017

Use Google Scholar for full citation

Recommended citation: Egidio Falotico, Lorenzo Vannucci, Alessandro Ambrosano, Ugo Albanese, Stefan Ulbrich, Juan Vasquez, Georg Hinkel, Jacques Kaiser, Igor Peric, Oliver Denninger, Nino Cauli, Murat Kirtay, Arne Roennau, Gudrun Klinker, Axel Von, Luc Guyot, Daniel Peppicelli, Pablo Martínez-Cañada, Eduardo Ros, Patrick Maier, Sandro Weber, Manuel Huber, David Plecher, Florian Röhrbein, Stefan Deser, Alina Roitberg, Patrick Smagt, Rüdiger Dillman, Paul Levi, Cecilia Laschi, Alois Knoll, Marc-Oliver Gewaltig, "Connecting Artificial Brains to Robots in a Comprehensive Simulation Framework: The Neurorobotics Platform." Frontiers in Neurorobotics, 2017.

Semi-Supervised Spiking Neural Network for One-Shot Object Appearance Learning

Published in In the proceedings of Proceedings of the 5th International Congress on Neurotechnology, Electronics and Informatics - NEUROTECHNIX,, 2017

Use Google Scholar for full citation

Recommended citation: Igor Peric, Robert Hangu, Jacques Kaiser, Stefan Ulbrich, Arne Roennau, Johann Zoellner, Ruediger Dillman, "Semi-Supervised Spiking Neural Network for One-Shot Object Appearance Learning." In the proceedings of Proceedings of the 5th International Congress on Neurotechnology, Electronics and Informatics - NEUROTECHNIX,, 2017.

Spiking convolutional deep belief networks

Published in In the proceedings of International Conference on Artificial Neural Networks (ICANN), 2017

Use Google Scholar for full citation

Recommended citation: Jacques Kaiser, David Zimmerer, J Tieck, Stefan Ulbrich, Arne Roennau, R{\"u}diger Dillmann, "Spiking convolutional deep belief networks." In the proceedings of International Conference on Artificial Neural Networks (ICANN), 2017.

Towards grasping with spiking neural networks for anthropomorphic robot hands

Published in In the proceedings of International Conference on Artificial Neural Networks, 2017

Use Google Scholar for full citation

Recommended citation: J Tieck, Heiko Donat, Jacques Kaiser, Igor Peric, Stefan Ulbrich, Arne Roennau, Marius Z{\"o}llner, R{\"u}diger Dillmann, "Towards grasping with spiking neural networks for anthropomorphic robot hands." In the proceedings of International Conference on Artificial Neural Networks, 2017.

Controlling a robot arm for target reaching without planning using spiking neurons

Published in In the proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC), 2018

Use Google Scholar for full citation

Recommended citation: J Tieck, Lea Steffen, Jacques Kaiser, Daniel Reichard, Arne Roennau, Rüdiger Dillmann, "Controlling a robot arm for target reaching without planning using spiking neurons." In the proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC), 2018.

Learning Movements by Imitation from Event-Based Visual Prediction

Published in In the proceedings of 2textsuperscriptnd Human Brain Project Student Conference, 2018

(Extended Abstract)

Recommended citation: Jacques Kaiser, Rüdiger Dillmann, "Learning Movements by Imitation from Event-Based Visual Prediction." In the proceedings of 2textsuperscriptnd Human Brain Project Student Conference, 2018.

Learning continuous muscle control for a multi-joint arm by extending proximal policy optimization with a liquid state machine

Published in In the proceedings of International Conference on Artificial Neural Networks, 2018

Use Google Scholar for full citation

Recommended citation: Juan Tieck, Marin Pogancic, Jacques Kaiser, Arne Roennau, Marc-Oliver Gewaltig, R{\"u}diger Dillmann, "Learning continuous muscle control for a multi-joint arm by extending proximal policy optimization with a liquid state machine." In the proceedings of International Conference on Artificial Neural Networks, 2018.

Learning to reproduce visually similar movements by minimizing event-based prediction error

Published in In the proceedings of International Conference on Biomedical Robotics and Biomechatronics (BIOROB), 2018

Use Google Scholar for full citation

Recommended citation: Jacques Kaiser, Svenja Melbaum, J. Tieck, Arne Roennau, Martin Butz, Rüdiger Dillmann, "Learning to reproduce visually similar movements by minimizing event-based prediction error." In the proceedings of International Conference on Biomedical Robotics and Biomechatronics (BIOROB), 2018.

Microsaccades for asynchronous feature extraction with spiking networks

Published in In the proceedings of International Conference on Development and Learning and Epigenetic Robotics (ICDL-EPIROB), 2018

Use Google Scholar for full citation

Recommended citation: Jacques Kaiser, Gerd Lindner, J. Tieck, Martin Schulze, Michael Hoff, Arne Roennau, R\"udiger Dillmann, "Microsaccades for asynchronous feature extraction with spiking networks." In the proceedings of International Conference on Development and Learning and Epigenetic Robotics (ICDL-EPIROB), 2018.

Microsaccades for neuromorphic stereo vision

Published in In the proceedings of International Conference on Artificial Neural Networks, 2018

Use Google Scholar for full citation

Recommended citation: Jacques Kaiser, Jakob Weinland, Philip Keller, Lea Steffen, J Tieck, Daniel Reichard, Arne Roennau, J{\"o}rg Conradt, R{\"u}diger Dillmann, "Microsaccades for neuromorphic stereo vision." In the proceedings of International Conference on Artificial Neural Networks, 2018.

Multi-modal motion activation for robot control using spiking neurons

Published in Biomedical Robotics and Biomechatronics (BioRob), 2018 IEEE International Conference on, 2018

Use Google Scholar for full citation

Recommended citation: J Tieck, Lea Steffen, Jacques Kaiser, Roenau Arne, Rüdiger Dillmann, "Multi-modal motion activation for robot control using spiking neurons." Biomedical Robotics and Biomechatronics (BioRob), 2018 IEEE International Conference on, 2018.

Triggering robot hand reflexes with human EMG data using spiking neurons

Published in In the proceedings of International Conference on Intelligent Autonomous Systems IAS-15, 2018

Use Google Scholar for full citation

Recommended citation: J. Tieck, Sandro Weber, Terrence Stewart, Arne Roennau, Rüdiger Dillmann, "Triggering robot hand reflexes with human EMG data using spiking neurons." In the proceedings of International Conference on Intelligent Autonomous Systems IAS-15, 2018.

Combining Motor Primitives for Perception Driven Target Reaching With Spiking Neurons

Published in International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 2019

Use Google Scholar for full citation

Recommended citation: J. Tieck, Lea Steffen, Jacques Kaiser, Daniel Reichard, Arne Roennau, Ruediger Dillmann, "Combining Motor Primitives for Perception Driven Target Reaching With Spiking Neurons." International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 2019.

talks

Learning Movements by Imitation from Event-Based Visual Prediction

Published:

In this talk, I introduce a new method for robots to learn movements from visual prediction. The method consists of two phases: learning a visual prediction model for a given movement, then minimizing the visual prediction error. The visual prediction model is learned from a single demonstration of the movement where only visual input is sensed.

Synaptic Plasticity Dynamics for Deep Continuous Local Learning

Published:

Understanding and deriving neural and synaptic plasticity rules that can enable hidden weights to learn is an ongoing quest in neuroscience and neuromorphic engineering. From a machine learning perspective, locality and differentiability are key issues of the spiking neuron model operations. In this poster presentation, it is shown that deep learning algorithms that locally approximate the gradient backpropagation updates using locally synthesized gradients overcome this challenge.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.