Zobrazeno 1 - 10
of 306
pro vyhledávání: '"Philipp, Christian"'
The generalized Gauss-Newton (GGN) optimization method incorporates curvature estimates into its solution steps, and provides a good approximation to the Newton method for large-scale optimization problems. GGN has been found particularly interesting
Externí odkaz:
http://arxiv.org/abs/2404.14875
We study the learning problem associated with spiking neural networks. Specifically, we consider hypothesis sets of spiking neural networks with affine temporal encoders and decoders and simple spiking neurons having only positive synaptic weights. W
Externí odkaz:
http://arxiv.org/abs/2404.04549
Autor:
Frieder, Simon, Pinchetti, Luca, Chevalier, Alexis, Griffiths, Ryan-Rhys, Salvatori, Tommaso, Lukasiewicz, Thomas, Petersen, Philipp Christian, Berner, Julius
Publikováno v:
NeurIPS 2023 Datasets and Benchmarks
We investigate the mathematical capabilities of two iterations of ChatGPT (released 9-January-2023 and 30-January-2023) and of GPT-4 by testing them on publicly available datasets, as well as hand-crafted ones, using a novel methodology. In contrast
Externí odkaz:
http://arxiv.org/abs/2301.13867
We study the generalization capacity of group convolutional neural networks. We identify precise estimates for the VC dimensions of simple sets of group convolutional neural networks. In particular, we find that for infinite groups and appropriately
Externí odkaz:
http://arxiv.org/abs/2212.09507
We study the training of deep neural networks by gradient descent where floating-point arithmetic is used to compute the gradients. In this framework and under realistic assumptions, we demonstrate that it is highly unlikely to find ReLU neural netwo
Externí odkaz:
http://arxiv.org/abs/2210.00805
We study the problem of reconstructing solutions of inverse problems when only noisy measurements are available. We assume that the problem can be modeled with an infinite-dimensional forward operator that is not continuously invertible. Then, we res
Externí odkaz:
http://arxiv.org/abs/2206.00934
Publikováno v:
In Neural Networks January 2024 169:462-474
