For Publishers
DiscoveryMetadataPeer reviewHostingPublishing
For Researchers
JoinPublishReviewCollect
Register
Blog
About
Search
Advanced search
My ScienceOpen
Search
For Publishers
For Researchers
Blog
About
Inviting an author to review:
PADS 2-02 - « Autotests pour le VIH : et vous ? » : connaissance et prévision d’utilisation selon une étude en ligne auprès du grand public
Find an author and click ‘Invite to review selected article’ near their name.
Search for authorsSearch for similar articles
0
views
3
references
 Top references
cited by
0
    
0 reviews
 Review
0
comments
 Comment
0
recommends
+1 Recommend
0 collections
    0
    shares
      42
      similar
       All similar
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      TED: Teaching AI to Explain its Decisions

      Preprint

      Read this article at

      ScienceOpenArXiv
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation, there is a growing demand for such systems to provide explanations for their decisions. Conventional approaches to this problem attempt to expose or discover the inner workings of a machine learning model with the hope that the resulting explanations will be meaningful to the consumer. In contrast, this paper suggests a new approach to this problem. It introduces a simple, practical framework, called Teaching Explanations for Decisions (TED), that provides meaningful explanations that match the mental model of the consumer. We illustrate the generality and effectiveness of this approach with two different examples, resulting in highly accurate explanations with no loss of prediction accuracy for these two examples.

          Related collections

          Most cited references3

          • Record: found
          • Abstract: found
          • Article: not found

          Simplicity and probability in causal explanation.

          Tania Lombrozo (2007)
          What makes some explanations better than others? This paper explores the roles of simplicity and probability in evaluating competing causal explanations. Four experiments investigate the hypothesis that simpler explanations are judged both better and more likely to be true. In all experiments, simplicity is quantified as the number of causes invoked in an explanation, with fewer causes corresponding to a simpler explanation. Experiment 1 confirms that all else being equal, both simpler and more probable explanations are preferred. Experiments 2 and 3 examine how explanations are evaluated when simplicity and probability compete. The data suggest that simpler explanations are assigned a higher prior probability, with the consequence that disproportionate probabilistic evidence is required before a complex explanation will be favored over a simpler alternative. Moreover, committing to a simple but unlikely explanation can lead to systematic overestimation of the prevalence of the cause invoked in the simple explanation. Finally, Experiment 4 finds that the preference for simpler explanations can be overcome when probability information unambiguously supports a complex explanation over a simpler alternative. Collectively, these findings suggest that simplicity is used as a basis for evaluating explanations and for assigning prior probabilities when unambiguous probability information is absent. More broadly, evaluating explanations may operate as a mechanism for generating estimates of subjective probability.
          Article 0 comments Cited 76 times – based on 0 reviews     Review now
            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            Rationale-Augmented Convolutional Neural Networks for Text Classification

            Ye Zhang, Iain Marshall, Byron Wallace (2016)
            We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or snippets) that support their overall document categorization, i.e., they provide rationales. Our model exploits such supervision via a hierarchical approach in which each document is represented by a linear combination of the vector representations of its component sentences. We propose a sentence-level convolutional model that estimates the probability that a given sentence is a rationale, and we then scale the contribution of each sentence to the aggregate document representation in proportion to these estimates. Experiments on five classification datasets that have document labels and associated rationales demonstrate that our approach consistently outperforms strong baselines. Moreover, our model naturally provides explanations for its predictions.
            Article 0 comments Cited 4 times – based on 0 reviews
            Preprint
                 Review now
              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Engineering Safety in Machine Learning

              Kush Varshney (2016)
              Machine learning algorithms are increasingly influencing our decisions and interacting with us in all parts of our daily lives. Therefore, just like for power plants, highways, and myriad other engineered sociotechnical systems, we must consider the safety of systems involving machine learning. In this paper, we first discuss the definition of safety in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes. Then we examine dimensions, such as the choice of cost function and the appropriateness of minimizing the empirical average training cost, along which certain real-world applications may not be completely amenable to the foundational principle of modern statistical machine learning: empirical risk minimization. In particular, we note an emerging dichotomy of applications: ones in which safety is important and risk minimization is not the complete story (we name these Type A applications), and ones in which safety is not so critical and risk minimization is sufficient (we name these Type B applications). Finally, we discuss how four different strategies for achieving safety in engineering (inherently safe design, safety reserves, safe fail, and procedural safeguards) can be mapped to the machine learning context through interpretability and causality of predictive models, objectives beyond expected prediction accuracy, human involvement for labeling difficult or rare examples, and user experience design of software.
              Article 0 comments Cited 2 times – based on 0 reviews
              Preprint
                   Review now
                Bookmark
                All references

                Author and article information

                Journal
                Publication date Created: 12 November 2018
                Article
                ArXiV ID: 1811.04896
                SO-VID: 38dff4be-d71b-475c-b4e0-c180caeaeb4e
                License:

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                Comments This article leverages some content from arXiv:1805.11648
                Categories cs.AI

                ScienceOpen disciplines: Artificial intelligence
                Data availability:
                ScienceOpen disciplines: Artificial intelligence

                Comments

                Comment on this article