Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Schürholt, Konstantin"'
Autor:
Schürholt, Konstantin
This thesis addresses the challenge of understanding Neural Networks through the lens of their most fundamental component: the weights, which encapsulate the learned information and determine the model behavior. At the core of this thesis is a fundam
Externí odkaz:
http://arxiv.org/abs/2410.05107
Autor:
Nauck, Christian, Gorantla, Rohan, Lindner, Michael, Schürholt, Konstantin, Mey, Antonia S. J. S., Hellmann, Frank
The geometry of a graph is encoded in dynamical processes on the graph. Many graph neural network (GNN) architectures are inspired by such dynamical systems, typically based on the graph Laplacian. Here, we introduce Dirac--Bianconi GNNs (DBGNNs), wh
Externí odkaz:
http://arxiv.org/abs/2407.12419
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61825-61853, 2024
This paper considers "model diagnosis", which we formulate as a classification problem. Given a pre-trained neural network (NN), the goal is to predict the source of failure from a set of failure modes (such as a wrong hyperparameter, inadequate mode
Externí odkaz:
http://arxiv.org/abs/2406.16988
Learning representations of well-trained neural network models holds the promise to provide an understanding of the inner workings of those models. However, previous work has either faced limitations when processing larger networks or was task-specif
Externí odkaz:
http://arxiv.org/abs/2406.09997
With growing size of Neural Networks (NNs), model sparsification to reduce the computational cost and memory demand for model inference has become of vital interest for both research and production. While many sparsification methods have been propose
Externí odkaz:
http://arxiv.org/abs/2304.13718
Publikováno v:
NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning
To mitigate climate change, the share of renewable needs to be increased. Renewable energies introduce new challenges to power grids due to decentralization, reduced inertia and volatility in production. The operation of sustainable power grids with
Externí odkaz:
http://arxiv.org/abs/2212.11130
In the last years, neural networks (NN) have evolved from laboratory environments to the state-of-the-art for many real-world problems. It was shown that NN models (i.e., their weights and biases) evolve on unique trajectories in weight space during
Externí odkaz:
http://arxiv.org/abs/2209.14764
Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an autoencoder trained
Externí odkaz:
http://arxiv.org/abs/2209.14733
Publikováno v:
First Workshop of Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022, Baltimore, Maryland, USA, PMLR 162, 2022
Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an autoencoder trained
Externí odkaz:
http://arxiv.org/abs/2207.10951
To mitigate climate change, the share of renewable energies in power production needs to be increased. Renewables introduce new challenges to power grids regarding the dynamic stability due to decentralization, reduced inertia, and volatility in prod
Externí odkaz:
http://arxiv.org/abs/2206.06369