On 4th August 2022 at 11:00 am our 13th Living La b Lecture will take place. This time Prof. Thomas Villmann will talk about \"Interpretable AI for Classification Learning – Towards Model Trustworthiness and Plausibility\".
After the overwhelmin g success of deep networks the need for smart classification models is inc reasingly providing an alternative in cases with hardware constraints. Fur ther\, interpretability is frequently demanded and leads to a better accep tance of machine learning tools. Additionally\, guarantees for robustness should provide classification certainty and model confidence.
In t his talk\, we reflect current developments of the learning vector quantiza tion model\, which was originally introduced by T. Kohonen in the 80s of t he last century but mathematically justified and significantly extended du ring the last years. Surprisingly\, these classifier models are highly fle xible and adjustable for various classification tasks while providing inte rpretability\, robustness as well as being smart models with low computati onal requirements. Prof. Thomas Villmann will present the most important d evelopments and theoretical results\, which ensure the required robustness \, certainty and flexibility while keeping the interpretability. Selected application cases illustrate the abilities of the models.
The Livi
ng Lab Lecture Series is free for everyone.
Language: English
To join the lecture please click here: Living Lab
Lecture (https://tud.link/i8zf)