Sort by
Refine Your Search
-
: Developing novel techniques to understand how information is processed within deep neural networks. Developing methods that achieve high accuracy while also being safe, interpretable, responsible, and reliable
-
. Investigate and implement optimum sampling strategies, including sparse and compressed sampling techniques. Explore the applicability of neural networks in clinical workflows, ensuring solutions are practical
-
exciting research direction. Join Us! Modern deep learning is progressing fast. Yet even the most advanced neural networks are paired with crucial limitations, such as making arbitrarily bad predictions
-
The Max Planck Artificial Intelligence Network (MP-AIX) has opened its general PhD call (applications via the ELLIS portal). The Multimodal Language Department, Max Planck Institute
-
networks overlap and differ across species, providing insights into the evolutionary origins of brain function and the neural basis of cognitive functions such as language, working memory, and theory-of-mind
-
workings of black-box machine learning models such as deep neural networks, they have severe drawbacks and limitations. The field of interpretable machine learning aims to fill this gap by developing