Monday 02.12.2019 18:00
Room 416-419

Seminar on Human & Machine Intelligence || NOTE: ALL SEMINAR MEETINGS ARE POSTPONED DUE TO THE CORONA CRISIS

Seminar on Human & Machine Intelligence

NOTE: ALL SEMINAR MEETINGS ARE POSTPONED DUE TO THE CORONA CRISIS

Organized by: 

Dr. Nori Jacoby (MPIEA)

Prof. Dr. Matthias Kaschube (FIAS & Goethe University Frankfurt)

Prof. Dr. Kristian Kersting (TU Darmstadt)

Prof. Dr. Stefan Kramer (Johannes Gutenberg University of Mainz)

Prof. Dr. Visvanathan Ramesh (Goethe University Frankfurt)

Prof. Dr. Gemma Roig (Goethe University Frankfurt)

Prof. Dr. Constantin A. Rothkopf (TU Darmstadt & FIAS)

Prof. Dr. Jochen Triesch (FIAS & Goethe University Frankfurt)

 

The disciplines of machine learning, brain sciences and complex systems engineering for AI is constantly evolving with new state-of-the-art techniques being introduced on a regular basis. There is an emerging ecosystem in the Frankfurt Rhein-Main region focusing on transdisciplinary aspects of intelligent systems where various facets of the development and impact of AI on sciences, humanities, and vice versa are being studied.  Our biweekly seminar complements other seminars in the region and is dedicated to fast-paced developments in the field and is particularly aimed at graduate students, postdocs, machine-learning researchers and cognitive scientists. The initial focus of the seminar will be on the latest developments in modern deep-learning applications, focusing mainly on domain-specific applications such as NLP, vision, and audio. We also plan to explore theoretical aspects of interest to development of third-wave AI systems that are context sensitive, enable interpretability/explainability of how results are arrived at, and provide transparency thus enabling fundamental insights on limits of algorithm designs in context. Other topics include the intersection between computational neuroscience, mathematical psychology and machine learning. Every meeting a presenter will provide a short introduction to the topic, followed by a description of the main findings of one or more papers which define the state-of-the art in the field. 
 

Click here to join our mailing list 
Click for the yearly calendar for the seminar
Click here to view/subscribe to our topic list


Future meetings: Mondays, 18:00-20:00  April 20, May 4, May 18, and June 8

Location: Max Planck Institute for Empirical Aesthetics

On March 16 (the following meeting), Gemma Roig will present on the topic of “Vision DNN Models and Their Relation for Explaining Different Areas of the Visual Cortex” POSTPONED

On April 20 Steffen Eger (TU Darmstadt) will update us on recent developments in NLP, with a focus on transformers title: "On the state-of-the-art in Evaluation for Machine Translation and summarization"

Abstract: In this talk, I will briefly (and on a high-level) talk about Transformer models and their use in state-of-the-art text classification models such as BERT, ALBERT and ROBERTA. Then I will talk about how we use BERT (and its variants) for evaluation of machine translation (MT) and text summarization systems, achieving much higher correlations with humans than classical evaluation measures such as BLEU or ROUGE. I will also talk about so-called reference-free evaluation for MT and summarization using multi- and cross-lingual models such as multi-lingual BERT in this context, highlighting some of their limitations and shortcomings. 

Previous meetings:

December 2, 2019: Prof. Dr. Christoph von der Malsburg (FIAS) on "AI: How to get out of the Human Shadow?"

January 13, 2020: Prof. Dr. Jochen Triesch (FIAS & Goethe University Frankfurt) on "Active Efficient Coding"

Februrary 3, 2020: Featuring: Timm Hess (Goethe University) on "Evaluation of Continual Machine Learning using Systematic Simulation"

Februrary 17, 2020:  Featuring: Prof. Dr. Alexander Gepperth (University of Applied Sciences Fulda) on "Real-world  continuous learning"

March 2, 2020:  Featuring: Dr. Peter Harrison, Federico Adolfi, Raja Marjieh and Dr. Nori Jacoby (MPIEA) on "Deep generative models in audition and music: Towards a unified framework"