Probabilistic Parametric Curves for Sequence Modeling

• Tác giả: Ronny Hug
• Ngôn ngữ: eng
• ISBN-13: 978-3731511984
• Thông tin xuất bản: Karlsruhe : KIT Scientific Publishing, 2022
• Mô tả vật lý: 1 electronic resource (226 p.)
• Bộ sưu tập: Tài liệu truy cập mở
• ID: 268724
• Chủ đề: 1. Neuronale Netzwerke; 2. Parametrische Kurven; 3. Probabilistische Sequenzmodellierung; 4. Stochastische Prozesse; 5. Maths for computer scientists

Tóm tắt

This work proposes a probabilistic extension to Bézier curves as a basis for effectively modeling stochastic processes with a bounded index set. The proposed stochastic process model is based on Mixture Density Networks and Bézier curves with Gaussian random variables as control points. A key advantage of this model is given by the ability to generate multi-mode predictions in a single inference step, thus avoiding the need for Monte Carlo simulation.