F
Frederik Hvilshøj
Researcher at Aarhus University
Publications - 8
Citations - 18
Frederik Hvilshøj is an academic researcher from Aarhus University. The author has contributed to research in topics: Counterfactual thinking & Counterfactual conditional. The author has an hindex of 3, co-authored 8 publications receiving 12 citations.
Papers
More filters
Posted Content
MeLIME: Meaningful Local Explanation for Machine Learning Models
TL;DR: This work introduces strategies to improve local explanations taking into account the distribution of the data used to train the black-box models, and produces more meaningful explanations compared to other techniques over different ML models, operating on various types of data.
Posted Content
Fast Fréchet Inception Distance
TL;DR: A novel algorithm, FastFID, is presented, which allows fast computation and backpropagation for FID and can efficiently evaluate generative model *during* training and construct adversarial examples for F ID.
Posted Content
ECINN: Efficient Counterfactuals from Invertible Neural Networks.
TL;DR: In this paper, a method, ECINN, was proposed to generate counterfactual examples in the time of only two evaluations of the classifier, which was shown to outperform established methods that generate heatmaps.
Posted Content
What if Neural Networks had SVDs
TL;DR: This work presents an algorithm that is fast enough to speed up several matrix operations, and increases the degree of parallelism of an underlying matrix multiplication where H is an orthogonal matrix represented by a product of Householder matrices.
Posted Content
Backpropagating through Fr\'echet Inception Distance
TL;DR: FastFID as mentioned in this paper uses Frechet Inception Distance (FID) as an additional loss function for GANs to improve their FID, which can efficiently train generative models with FID as a loss function.