A model explanation system

@article{Turner2016AME,
  title={A model explanation system},
  author={Ryan Turner},
  journal={2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)},
  year={2016},
  pages={1-6},
  url={https://api.semanticscholar.org/CorpusID:7675379}
}
A scoring system is derived for finding explanations for black box classifiers with finite sample guarantees based on formal requirements and the explanations are assumed to take the form of simple logical statements.
View on IEEE
blackboxworkshop.org
76 Citations
Highly Influential Citations
4
Background Citations
34
Methods Citations
20
Results Citations
1

Figures and Tables from this paper

76 Citations

A Model Explanation System: Latest Updates and Extensions

This paper describes extensions to Turner (2015), which is referred to frequently in the text, and focuses on explaining positive predictions (alerts), but the presented methodology is symmetrically applicable to negative predictions.

A Survey on the Explainability of Supervised Machine Learning

This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning, and a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions.

Interpretable Explanations of Black Boxes by Meaningful Perturbation

A general framework for learning different kinds of explanations for any black box algorithm is proposed and the framework to find the part of an image most responsible for a classifier decision is specialised.

Towards Interrogating Discriminative Machine Learning Models

The results indicate that the proposed approach not only outperforms the state-of-the-art technique in explaining individual decisions but also provides users with an ability to discover the vulnerabilities of a learning model.

Explanations for Attributing Deep Neural Network Predictions

This chapter introduces Meta-Predictors as Explanations, a principled framework for learning explanations for any black box algorithm, and Meaningful Perturbations, an instantiation of the paradigm applied to the problem of attribution.

Unjustified Classification Regions and Counterfactual Explanations in Machine Learning

This paper focuses on the notion of explanation justification, defined as connectedness to ground-truth data, in the context of counterfactuals, and shows that state-of-the-art post-hoccounterfactual approaches can minimize the impact of this risk by generating less local explanations.

Explanation by Progressive Exaggeration

This work proposes a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class by gradually changes the posterior probability from its original class to its negation.

Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications

ExplainExplore: Visual Exploration of Machine Learning Explanations

This work introduces EXPLAINEXPLORE: an interactive explanation system to explore explanations that fit the subjective preference of data scientists, and leverages the domain knowledge of the data scientist to find optimal parameter settings and instance perturbations.

Machine Learning Explainability Through Comprehensible Decision Trees

This work focuses on explaining black-box models by using decision trees of limited size as a surrogate model and proposes an approach based on microaggregation to achieve a trade-off between comprehensibility and representativeness of the surrogate model on the one side and privacy of the subjects used for training the black-boxes on the other side.
...

23 References

Survey and critique of techniques for extracting rules from trained artificial neural networks

On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes

It is shown, contrary to a widely-held belief that discriminative classifiers are almost always to be preferred, that there can often be two distinct regimes of performance as the training set size is increased, one in which each algorithm does better.

Comprehensible Credit Scoring Models Using Rule Extraction from Support Vector Machines

This paper provides an overview of the recently proposed rule extraction techniques for SVMs and introduces two others taken from the artificial neural networks domain, being Trepan and G-REX, which rank at the top of comprehensible classification techniques.

Making machine learning models interpretable

This paper is a brief introduction to the special session on interpretable models in machine learning, organized as part of the 20 th European Symposium on Artificial Neural Networks, Computational In- telligence and Machine Learning, with an overview of the context of wider research on interpretability of machine learning models.

Induction of decision trees

This paper summarizes an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail, which is described in detail.

A review of machine learning approaches to Spam filtering

Regression Shrinkage and Selection via the Lasso

A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.

POSTERIOR PREDICTIVE ASSESSMENT OF MODEL FITNESS VIA REALIZED DISCREPANCIES

This paper considers Bayesian counterparts of the classical tests for good- ness of fit and their use in judging the fit of a single Bayesian model to the observed data. We focus on posterior…

Do we need hundreds of classifiers to solve real world classification problems?

The random forest is clearly the best family of classifiers (3 out of 5 bests classi fier behavior are RF), followed by SVM, neural networks and boosting ensembles (5 and 3 members in the top-20, respectively), and a few models are clearly better than the remaining ones.

Data mining with decision trees and decision rules