Normalization Effects on Neural Networks: Generalization and High-Dimensional Applications - SIAM FME Talk
Society for Industrial and Applied Mathematics via YouTube
PowerBI Data Analyst - Create visualizations and dashboards from scratch
Finance Certifications Goldman Sachs & Amazon Teams Trust
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Attend a virtual talk in the SIAM Activity Group on Financial Mathematics and Engineering series featuring speaker Konstantinos Spiliopoulos from Boston University. Explore the effects of normalization on neural networks, focusing on generalization properties and performance in high-dimensional scenarios. Gain insights into the asymptotic expansion of neural network outputs, the relationship between normalization and mean field scaling, and their impact on bias-variance trade-offs. Discover how these theoretical findings translate to practical applications through numerical studies on popular datasets like MNIST and CIFAR10. Learn about a novel deep learning algorithm for solving high-dimensional partial differential equations, including its application to option pricing in up to 500 dimensions. Moderated by Agostino Capponi from Columbia University, this 57-minute talk offers valuable knowledge for researchers and practitioners in mathematical finance and engineering.
Syllabus
Twenty first SIAM Activity Group on FME Virtual Talk Series
Taught by
Society for Industrial and Applied Mathematics