Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Wäldchen, Stephan"'
Autor:
Wäldchen, Stephan
Recent progress towards theoretical interpretability guarantees for AI has been made with classifiers that are based on interactive proof systems. A prover selects a certificate from the datapoint and sends it to a verifier who decides the class. In
Externí odkaz:
http://arxiv.org/abs/2306.04505
We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of lower bounds on the mutual information between selected features and the
Externí odkaz:
http://arxiv.org/abs/2206.00759
One of the goals of Explainable AI (XAI) is to determine which input components were relevant for a classifier decision. This is commonly know as saliency attribution. Characteristic functions (from cooperative game theory) are able to evaluate parti
Externí odkaz:
http://arxiv.org/abs/2202.11797
Autor:
Macdonald, Jan, Wäldchen, Stephan
We give a complete characterisation of families of probability distributions that are invariant under the action of ReLU neural network layers. The need for such families arises during the training of Bayesian networks or the analysis of trained neur
Externí odkaz:
http://arxiv.org/abs/2112.06532
We formalise the widespread idea of interpreting neural network decisions as an explicit optimisation problem in a rate-distortion framework. A set of input features is deemed relevant for a classification decision if the expected classifier score re
Externí odkaz:
http://arxiv.org/abs/1905.11092
For a Boolean function $\Phi\colon\{0,1\}^d\to\{0,1\}$ and an assignment to its variables $\mathbf{x}=(x_1, x_2, \dots, x_d)$ we consider the problem of finding the subsets of the variables that are sufficient to determine the function value with a g
Externí odkaz:
http://arxiv.org/abs/1905.09163
Autor:
Lapuschkin, Sebastian, Wäldchen, Stephan, Binder, Alexander, Montavon, Grégoire, Samek, Wojciech, Müller, Klaus-Robert
Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and a
Externí odkaz:
http://arxiv.org/abs/1902.10178
Publikováno v:
Phys. Rev. Lett. 116, 020502 (2016)
Entanglement distillation refers to the task of transforming a collection of weakly entangled pairs into fewer highly entangled ones. It is a core ingredient in quantum repeater protocols, needed to transmit entanglement over arbitrary distances in o
Externí odkaz:
http://arxiv.org/abs/1503.04822
Autor:
Kreft, Bernhard *, Tzschätzsch, Heiko, Schrank, Felix, Bergs, Judith, Streitberger, Kaspar-Josche, Wäldchen, Stephan, Hetzer, Stefan, Braun, Jürgen *, Sack, Ingolf
Publikováno v:
In Ultrasound in Medicine & Biology April 2020 46(4):936-943
We propose a new type of multi-agent interactive classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of bounds on the mutual information of the features selected by t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51b2e89cd2ee4df84c318c58440aba73
http://arxiv.org/abs/2206.00759
http://arxiv.org/abs/2206.00759