Seminar Details
Mixed Frequency Data Inputs for Recurrent Neural Networks
- Start Date: April 23, 2020
- Event Start Time: 5:00 PM
- Event End Time: 6:00 PM
- Seminar Series: Experimental Math Seminar
- Presenter(s): Stephen Chen - Princeton University
- Event Location: Online Event
- Event Additional Info: <p><strong>SPECIAL NOTE: This seminar is presented online only.</strong></p> <p><strong>You can join via ZOOM or by clicking this link </strong><a href="https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fprinceton.zoom.us%2Fj%2F843514245&data=02%7C01%7Clindac%40dimacs.rutgers.edu%7C24503c109b464dc8360608d7e2cf770a%7Cb92d2b234d35447093ff69aca6632ffe%7C1%7C0%7C637227252995796331&sdata=Ibe5mnDmTDaWUy13L6nHxj79qXOt4nfZaE4wzbelh9M%3D&reserved=0">https://princeton.zoom.us/j/843514245</a></p> <p> </p> <p>For further information see: <a href="https://sites.math.rutgers.edu/~zeilberg/expmath/">https://sites.math.rutgers.edu/~zeilberg/expmath/</a></p>
- Presentation Type: Stand Alone Presentation
- Abstract:
Observations sampled at different frequencies provide multi-level details. How to effectively use them remains a challenging task. We can aggregate all the data to the lowest-frequency level, or we can fill all the missing data to the highest-frequency level. Is there a better way to utilize the information without eliminating the details or introducing noise? We here provide a recurrent neural network model for mixed frequency data, providing convergence proof, error estimation, and some numerical results.