Yuksel Splines for Probabilistic Sequence Prediction
Description
Current methods for sequence prediction often fail to account for higher-ordercontinuity. This results in the prediction of sequences that might be continuous but not
physically viable as I investigate higher-order smoothness in terms of velocity and
acceleration. Hence, I propose a Yuksel Spline-based model that is not only capable of
predicting curves that are guaranteed to be C^2 continuous but, also efficient to compute
as well. Characteristic properties of the models are demonstrated over toy examples and
sequence prediction tasks.
Date Created
The date the item was original created (prior to any relationship with the ASU Digital Repositories.)
2024
Agent
- Author (aut): Tokas, Bhanu
- Thesis advisor (ths): Kerner, Hannah
- Committee member: Lee, Kookjin
- Committee member: Boscovic, Dragan
- Publisher (pbl): Arizona State University