Interpretability of deep learning models: A survey of results

S Chakraborty, R Tomsett… - … , advanced & trusted …, 2017‏ - ieeexplore.ieee.org
Deep neural networks have achieved near-human accuracy levels in various types of
classification and prediction tasks including images, text, speech, and video data. However …

Auditing black-box models for indirect influence

P Adler, C Falk, SA Friedler, T Nix, G Rybeck… - … and Information Systems, 2018‏ - Springer
Data-trained predictive models see widespread use, but for the most part they are used as
black boxes which output a prediction or score. It is therefore hard to acquire a deeper …

Improving the quality of explanations with local embedding perturbations

Y Jia, J Bailey, K Ramamohanarao, C Leckie… - Proceedings of the 25th …, 2019‏ - dl.acm.org
Classifier explanations have been identified as a crucial component of knowledge
discovery. Local explanations evaluate the behavior of a classifier in the vicinity of a given …

Methods for explaining Top-N recommendations through subgroup discovery

M Iferroudjene, C Lonjarret, C Robardet… - Data Mining and …, 2023‏ - Springer
Abstract Explainable Artificial Intelligence (XAI) has received a lot of attention over the past
decade, with the proposal of many methods explaining black box classifiers such as neural …

A comparison of constant curvature forward kinematics for multisection continuum manipulators

A Chawla, C Frazelle, I Walker - 2018 Second IEEE …, 2018‏ - ieeexplore.ieee.org
Over the past few years, modeling of continuum robots has been the subject of considerable
attention in the research community. In this paper, we compare a set of forward kinematic …

Declarative aspects in explicative data mining for computational sensemaking

M Atzmueller - … Programming, DECLARE 2017, Unifying INAP, WFLP …, 2018‏ - Springer
Computational sensemaking aims to develop methods and systems to “make sense” of
complex data and information. The ultimate goal is then to provide insights and enhance …

Why should i trust this item? explaining the recommendations of any model

C Lonjarret, C Robardet, M Plantevit… - 2020 IEEE 7th …, 2020‏ - ieeexplore.ieee.org
Explainable AI has received a lot of attention over the past decade, with the proposal of
many methods explaining black box classifiers such as neural networks. Despite the …

Exploiting patterns to explain individual predictions

Y Jia, J Bailey, K Ramamohanarao, C Leckie… - … and Information Systems, 2020‏ - Springer
Users need to understand the predictions of a classifier, especially when decisions based
on the predictions can have severe consequences. The explanation of a prediction reveals …

Softmax-based classification is k-means clustering: Formal proof, consequences for adversarial attacks, and improvement through centroid based tailoring

S Hess, W Duivesteijn, D Mocanu - arxiv preprint arxiv:2001.01987, 2020‏ - arxiv.org
We formally prove the connection between k-means clustering and the predictions of neural
networks based on the softmax activation layer. In existing work, this connection has been …

Exceptionally monotone models—the rank correlation model class for exceptional model mining

L Downar, W Duivesteijn - Knowledge and Information Systems, 2017‏ - Springer
Abstract Exceptional Model Mining strives to find coherent subgroups of the dataset where
multiple target attributes interact in an unusual way. One instance of such an investigated …