Human-Centered AI for smart farming BOKU Tulln March, 9, 2023

On March, 9, 2023 at the BOKU Tulln, we were guest speakers at the traditional Schlumberger lectures. For us a wonderful opportunity to show what Human-Centered AI can do for smart farming. Thanks to the organizers Michaela Griesser and Astrid Forneck from the Department of Crop Sciences (DNW) lead by Hans-Peter Kaul. Looking forward to help to discover the causality of berry shrivel (Traubenwelke) with methods from deep geometric learning for knowledge discovery from point cloud data.

Inaugural Lecture Andreas Holzinger Human-Centered AI

The inaugural lecture of Andreas Holzinger on Monday, Nov, 7, 2022, 18:00 on Human-Centered AI is open to the public – you are cordially welcome

Research Seminar, Wednesday, December, 9, 2020

HCAI research seminar: “Towards Games in explainable AI” and “simultaneous neural nets and synthetiziced literate-logic-programs”

Miniconf Thursday, 20th December 2018: Raphaël Marée

Raphaël MARÉE  from the Montefiori Institute, Unviersity of Liege will visit us in week 51 and give a lecture on

Open and Collaborative Digital Pathology using Cytomine

When: Thursday, 20th December, 2018, at 10:00
Where: BBMRI Conference Room (joint invitation of BBMRI, ADOPT and HCI-KDD)
Address: Neue Stiftingtalstrasse 2/B/6, A-8010 Graz, Austria

Download pdf, 72kB

Abstract:

In this talk Raphael Maree will present the past, present, and future of Cytomine.
Cytomine [1], [2]  is an open-source software, continuously developed since 2010. It is based on modern web and distributed software development methodologies and machine learning, i.e. deep learning. It provides remote and collaborative features so that users can readily and securely share their large-scale imaging data worldwide. It relies on data models that allow to easily organize and semantically annotate imaging datasets in a standardized way (e.g. to build pathology atlases for training courses or ground-truth datasets for machine learning). It efficiently supports digital slides produced by most scanner vendors. It provides mechanisms to proofread and share image quantifications produced by machine/deep learning-based algorithms. Cytomine can be used free of charge and it is distributed under a permissive license. It has been installed at various institutes worldwide and it is used by thousands of users in research and educational settings.

Recent research and developments will be presented such as our new web user interfaces and new modules for multimodal and multispectral data (Proteomics Clin Appl, 2019), object recognition in histology and cytology using deep transfer learning (CVMI 2018), user behavior analytics in educational settings (ECDP 2018), as well as our new reproducible architecture to benchmark bioimage analysis workflows.

Short Bio:

Raphaël Marée received the PhD degree in computer science in 2005 from the University of Liège, Belgium, where he is now working at the Montefiore EE&CS Institute (https://www.montefiore.ulg.ac.be/~maree/). In 2010 he initiated the CYTOMINE research project (https://uliege.cytomine.org/), and since 2017 he is also co-founder of the not-for-profit Cytomine cooperative (https://cytomine.coop). His research interests are in the broad area of machine learning, computer vision techniques, and web-based software development, with specific focus on their applications on big imaging data such as in digital pathology and life science research, while following open science principles.

[1]       Raphaël Marée, Loïc Rollus, Benjamin Stévens, Renaud Hoyoux, Gilles Louppe, Rémy Vandaele, Jean-Michel Begon, Philipp Kainz, Pierre Geurts & Louis Wehenkel 2016. Collaborative analysis of multi-gigapixel imaging data using Cytomine. Bioinformatics, 32, (9), 1395-1401, doi:10.1093/bioinformatics/btw013.

[2] https://www.cytomine.org 

Google Scholar Profile of Raphael Maree:
https://scholar.google.com/citations?user=qG66mF8AAAAJ&hl=en

Homepage of Raphael Maree:
https://www.montefiore.ulg.ac.be/~maree/

Yoshua Bengio emphasizes: Deep Learning needs Deep Understanding !

Yoshua BENGIO from the Canadian Institute for Advanced Research (CIFAR) emphasized during his workshop talk “towards disentangling underlying explanatory factors”  (cool title) at the ICML 2018 in Stockholm, that the key for success in AI/machine learning is to understand the explanatory/causal factors and mechanisms. This means generalizing beyond identical independent data (i.i.d.) – and this is crucial for our domain in medcial AI, because current machine learning theories and models are strongly dependent on this iid assumption, but applications in the real-world (we see this in the medical domain every day!) often require learning and generalizing in areas simply not seen during the training epoch. Humans interestingly are able to protect themselves in such situations, even in situations which they have never seen before. Here a longer talk (1:17:04) at Microsoft Research Redmond on January, 22, 2018 – awesome – enjoy the talk, I recommend it cordially to all of my students!

CD-MAKE Keynote by Klaus-Robert MÜLLER

Prof. Dr. Klaus-Robert MÜLLER from the TU Berlin was our keynote speaker on Tuesday, August, 28th, 2018 during our CD-MAKE conference at the University of Hamburg, see:

Klaus-Robert emphasized in his talk the “right of explanation” by the new European Union General Data Protection Regulations, but also shows some diffulties, challenges and future research directions in the area what is now called explainable AI.  Here you find his presentation slides with friendly permission from Klaus-Robert MÜLLER:
https://human-centered.ai/wordpress/wp-content/uploads/2018/08/cd-make-N-muller18.pdf
(3,52 MB)

Here some snapshots from the keynote:

Thanks to Klaus-Robert for his presentation!