<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText">ETH Foundations of Data Science (ETH-FDS) announces and invites you to the annual Stiefel Lecture.<br>
<br>
The Stiefel Lecture 2025 will be given by Prof. Andrew Stuart, Caltech, USA, on<br>
<br>
Titel: Allowing Image And Text Data To Communicate (Attention Is Sometimes Useful)<br>
<br>
Abstract: A fundamental problem in artificial intelligence is the question of how to simultaneously deploy data from different sources such as audio, image, text and video; such data is known as multimodal. In this talk I will focus on the canonical problem
of aligning image and text data, and describe some of the mathematical ideas underlying the challenge of allowing them to communicate. I will describe the encoding of text and image in Euclidean spaces and describe contrastive learning methodology to identify
and learn embeddings which align these two modalities. In so doing I will then describe the attention mechanism, a form of nonlinear transform that quantifies correlation in vector-valued sequences. Attention turns out to be useful beyond this specific context,
and I will show how it may be used to design and learn maps between Banach spaces or between metric spaces of probability measures. The former is useful for accelerating MCMC, and the latter for nonlinear filtering.<br>
<br>
Monday, 12 May 2025 at 17:15.<br>
ETH Zurich, HG F 30 (Audi Max)<br>
<br>
The talk will be followed by an apero.<br>
<br>
The Stiefel Lecture has been created in honor of Eduard Stiefel (1909-1978) who was professor of mathematics at ETH Zürich. Stiefel has been the driving force for establishing "electronic scientific computing" with ERMETH (Elektronische Rechenmaschine der ETH).
This became a landmark in computational and mathematical sciences with a huge impact to a broad range of applications in engineering and natural science. Stiefel has made fundamental and lasting contributions in mathematics, including the introduction of the
Stiefel-Whitney classes, the Stiefel manifold and the conjugate gradient method. Stiefel advised 63 PhD students, many of whom became leaders in their field.<br>
<br>
We cordially invite you to this year's Stiefel Lecture with Andrew Stuart and look forward to meeting you there.<br>
<br>
With kind regards,<br>
<br>
Peter Bühlmann<br>
ETH Foundations of Data Science<br>
<br>
<a href="https://math.ethz.ch/sfs/eth-foundations-of-data-science.html">https://math.ethz.ch/sfs/eth-foundations-of-data-science.html</a><br>
<a href="https://math.ethz.ch/sfs/news-and-events/stiefel-lectures.html">https://math.ethz.ch/sfs/news-and-events/stiefel-lectures.html</a><br>
<a href="https://library.ethz.ch/standorte-und-medien/plattformen/kurzportraets/eduard-stiefel-1909-1978.html">https://library.ethz.ch/standorte-und-medien/plattformen/kurzportraets/eduard-stiefel-1909-1978.html</a><br>
<a href="http://www.ethistory.ethz.ch/rueckblicke/departemente/dinfk/forschung/">http://www.ethistory.ethz.ch/rueckblicke/departemente/dinfk/forschung/</a><br>
</div>
</span></font></div>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText"><br>
<br>
<br>
</div>
</span></font></div>
</body>
</html>