Institute
General information about the institute, such as our mission statement, organizational structure, staff directory, history, directions, etc.

See More
Research
Scientific profile with all research groups, topics, collaborations, as well as columns on research at the institute.

See More
News
News and press releases about the institute, as well as a media archive.

See More
- News Overview
- Press Releases
Events
Overview of all events around the institute, such as talks, seminars, lectures, workshops, conferences and public events.

See More
Publications
Overview of all scientific publications of the institute, as well as our preprint and software repositories.

See More
Career
Information on open positions at the institute, benefits of working with us, graduate school, and postdoctoral supervision.

See More

MPI for Mathematics in the Sciences

Live Stream

seminar

08.05.20 22.05.20

Math Machine Learning Group Seminar


22.05.20	Hui Jin (University of California, Los Angeles) Implicit bias of gradient descent on wide neural networks no abstract available
15.05.20	Thomas Merkh (University of California, Los Angeles) Recurrences and transfer methods for counting activation patterns in CNNs no abstract available
08.05.20	Yoni Dukler (University of California, Los Angeles) Deep Learning for Self Driving In this talk, I will give an overview of the current state and common methodologies of self driving technologies. Due to the advancements in hardware, and the wealth of data being collected by such systems, deep learning algorithms are emerging to be crucial and I will survey the common uses of deep learning for self driving. Lastly as a theoretician, I will go over avenues and challenges in self driving systems that can benefit from improved theoretical understanding and deep learning theory. The purpose of this talk is to introduce deep learning researchers to the field and present some of the most pressing issues faced by self driving practitioners in the hopes of advancing the field as a whole.

MPI for Mathematics in the Sciences Contact via Mail