In this paper, a neural network approach is suggested to the product design analysis.
Namely, fractional-order neural network models are proposed as more flexible mechanism …

Lipschitz bounded neural networks are certifiably robust and have a good trade-off between
clean and certified accuracy. Existing Lipschitz bounding methods train from scratch and are …

Artificial neural networks are at the core of recent advances in Artificial Intelligence. One of
the main challenges faced today, especially by companies likeThales designing advanced …

In this paper, we advance the concept of shrinking weights to train certifiably robust models
from the fresh perspective of gradient-based bi-level optimization. Lack of robustness …

This thesis explores the characteristics and applications of Lipschitz networks in machine
learning tasks. First, the framework of" optimization as a layer" is presented, showcasing …

This thesis deals with the application of neural networks in solving electrical motor problems.
Chapter 2 contributes to identifying a neural network that can learn the multivariate …

In order to improve the accuracy of autonomous precision landing of UAVs and enhance the
adaptability of autonomous landing of UAVs, a new type of UAV tracking algorithm is …