Talks, Presentations, and Workshops

In collaboration with ARIC, I had my second workshop on reinforcement learning. This workshop was followed by a hands-on session about RL.

I was invited as speaker to the Remote Brown Bag Sessions which are orginized by Artificial Intelligence Center Hamburg (ARIC). In this talk, I presented our work on Continuous Acoustic Emotion Classification which we could reduce latency and improve the accuracy for critical cases.

The (online) workshop is organized by Hamburger Informatik Technologie-Center e.V. (HITeC) and Artificial Intelligence Center Hamburg e.V. (ARIC) on 9th, 16th, and 23rd April 2020. The focus of the workshop was on optimizing hyperparameters of deep learning models with Bayesian optimization.

My second internal workshop at HITeC was about deep learning with Pytorch and AutoML. I introduced the basics of deep learning and how to implement a classification problem in Pytorch. Then, I introduced one of the latest AutoML approach called BOHB for hyperparameter optimization.

I had an internal workshop at HITeC on Introduction to Gaussian Process and Bayesian Optimization. The content of the workshop was: Basics from Statistics Gaussian Process Bayesian Optimization

I jointly presented our paper On the Robustness of Speech Emotion Recognition for Human-Robot Interaction with Deep Neural Networks during the interactive section. Also, on the last day of the conference, I attended the Machine Learning in Robot Motion Planning workshop to present our work on Neural End-to-End Learning of Reach for Grasp Ability with a 6-DoF Robot Arm.

We organized a PhD students conference focused safety and interaction quality. I also had a chance to present my progress in this conference.

I presented 3 posters at ICRA main conference, Workmate workshop and PhD forum. The first presentation was “Emorl: Continuous acoustic emotion classification using deep reinforcement learning” at ICRA 2018. I also presented “Learning spatial representation for safe human-robot collaboration in joint manual tasks” at the Workmate workshop at ICRA 2018.

In this presentation, I talked about AI and public concerns. The purpose of the talk was to give some intuition for a public audience that what is the research focus and methodological tools in AI.

I presented our work on Deep Reinforcement Learning using Symbolic Representation for Performing Spoken Language Instructions at 2nd Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics (BAILAR). This workshop was part of the 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).