In order to ease the analysis of error propagation in neuromorphic computing and to get a better understanding of spiking neural networks (SNN), we address the problem of mathematical analysis of SNNs as endomorphisms that map spike trains to ...

Display Omitted

• Understanding leaky-integrate-and-fire (LIF) as signal-to-spike-train quantization operator.
• Formula for the quantization error based on the Alexiewicz norm.
• Determination of a quasi-isometric relationship between incoming and ...

Recent work has proposed novel data augmentation methods to improve the adversarial robustness of deep neural networks. In this paper, we re-evaluate such methods through the lens of different metrics that characterize the augmented manifold, ...

• Augmentation methods for adversarial robustness are often not tested in isolation.
• They are often tested on one single value of augmentation probability.
• They improve robustness only when combined with classical augmentations.
• ...

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative of the data ...

• A novel metric-based regularization for domain-invariant training of neural networks.

A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature ...