BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:Seminar: Weinan E (Princeton University, Beijing Institute of Big Data Research), A Mathematical Perspective of Machine Learning
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1610222_0
SUMMARY:Seminar: Weinan E (Princeton University, Beijing Institute of Big Data Research), A Mathematical Perspective of Machine Learning
DESCRIPTION:<p>	<drupal-media data-entity-type="media" data-entity-uuid="b23ff50a-e032-4c3d-a601-0c657342b60a" alt="Weinan E" data-view-mode="hwp_small"></drupal-media></p><p>	<strong>Title:</strong> A Mathematical Perspective of Machine Learning</p><p>	<strong>Speaker:</strong> Weinan E, Princeton University</p><p>	<strong>Zoom:</strong> <a href="https://harvard.zoom.us/j/779283357?pwd=MitXVm1pYUlJVzZqT3lwV2pCT1ZUQT09" title="">https://harvard.zoom.us/j/779283357?pwd=MitXVm1pYUlJVzZqT3lwV2pCT1ZUQT09</a></p><p>	<strong>Abstract:</strong> The heart of modern machine learning (ML) is the approximation of high-dimensional functions. Traditional approaches, such as approximation by piecewise polynomials, wavelets, or other linear combinations of fixed basis functions, suffer from the curse of dimensionality (CoD). This does not seem to be the case for the neural network-based ML models. To quantify this, we need to develop the corresponding mathematical framework. At the same time, we might be able to use ML to solve problems in computational science that we could not solve before due to CoD. In this talk, I will report the progress made so far at the theoretical front, and highlight the main remaining challenges. I will also discuss some examples along the lines of "AI for Science".</p><p>	 </p>
LOCATION:https://harvard.zoom.us/j/779283357?pwd=MitXVm1pYUlJVzZqT3lwV2pCT1ZUQT09  
STATUS:CONFIRMED
DTSTART:20211026T133000Z
DTEND:20211026T133000Z
END:VEVENT
END:VCALENDAR