When Can Transformers Count to n?
Large language models based on the transformer architectures can solve highly complex
tasks. But are there simple tasks that such models cannot solve? Here we focus on very …
tasks. But are there simple tasks that such models cannot solve? Here we focus on very …
Decomposition Polyhedra of Piecewise Linear Functions
MC Brandenburg, M Grillo, C Hertrich - arXiv preprint arXiv:2410.04907, 2024 - arxiv.org
In this paper we contribute to the frequently studied question of how to decompose a
continuous piecewise linear (CPWL) function into a difference of two convex CPWL …
continuous piecewise linear (CPWL) function into a difference of two convex CPWL …
[HTML][HTML] Combining Dielectric and Hyperspectral Data for Apple Core Browning Detection
H Liu, J He, Y Shi, Y Bi - Applied Sciences, 2024 - mdpi.com
Apple core browning not only affects the nutritional quality of apples, but also poses a health
risk to consumers. Therefore, there is an urgent need to develop a fast and reliable non …
risk to consumers. Therefore, there is an urgent need to develop a fast and reliable non …
Efficient Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
AM Neuman, PC Petersen - arXiv preprint arXiv:2404.04549, 2024 - arxiv.org
We study the learning problem associated with spiking neural networks. Specifically, we
consider hypothesis sets of spiking neural networks with affine temporal encoders and …
consider hypothesis sets of spiking neural networks with affine temporal encoders and …
Depth Separations in Neural Networks: Separating the Dimension from the Accuracy
We prove an exponential separation between depth 2 and depth 3 neural networks, when
approximating an $\mathcal {O}(1) $-Lipschitz target function to constant accuracy, with …
approximating an $\mathcal {O}(1) $-Lipschitz target function to constant accuracy, with …