Continuous Spline Approximation with TensorFlow Gradient Descent Optimizers - Online-Präsentation Forschungsergebnisse

Hannes Waclawek, Junior Researcher am Studiengang Informationstechnik & System-Management, stellt am 02.02.2022 um 16:00 Uhr neueste Forschungsergebnisse vor: C^k-continuous Spline Approximation with TensorFlow Gradient Descent Optimizers. Interessierte können gerne online daran teilnehmen.

Kurzbeschreibung Vortrag

Motivated by cam profile generation in mechatronics, we investigate function approximation by C^k-continuous splines using gradient descent optimization provided by the machine learning framework TensorFlow.

First, we investigate the convergence behavior of the model parameters of a spline model with respect to different loss functions, specifically for L²-approximation error and C^k-continuity, by means of different TensorFlow optimizers. In particular, we propose a parameter regularization that allows SGD (with/without Nesterov-Momentum) to converge. We show that Adam (or rather AMSGrad) generally performs best, yet the rather simple SGD can be close to competitive with our regularization.

Wann? MI 2. Feb 2022, 16:00
Wo? Online
Wer? Hannes Waclawek

Der Vortrag findet im Rahmen der Reading Group der "Smart Factory & Edge Computing"-Forschungsgruppe des Studiengangs Informationstechnik & System-Management statt.