Safe and Interpretable Machine Learning: A Methodological Review

Otte, Clemens

doi:10.1007/978-3-642-32378-2_8

Cited by 38 publications

(21 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…People are working on more interpretable methods, but there seem to tradeoffs involved in making such systems more interpretable (Vellido, Guerrero and Lisboa 2012;Lisboa 2013;Otte 2013;Chase Lipton 2015;Zeng, Ustun and Rudin 2015). 22 Finally, compounding these two problems, there is the fact algorithms are not singular phenomena.…”

Section: And Why Wouldn't We If We Are Promised Slimmer Waistlines mentioning

confidence: 99%

The Threat of Algocracy: Reality, Resistance and Accommodation

2016

View full text Add to dashboard Cite

EnhancementOne of the most noticeable trends in recent years has been the increasing reliance of public decision-making processes (bureaucratic, legislative and legal) on algorithms, i.e. computer programmed step-by-step instructions for taking a given set of inputs and producing an output. The question raised by this article is whether the rise of such algorithmic governance creates problems for the moral or political legitimacy of our public decision-making processes. Ignoring common concerns with data protection and privacy, it is argued that algorithm-driven decisionmaking does pose a significant threat to the legitimacy of such processes. Modeling my argument on Estlund's threat of epistocracy, I call this the 'threat of algocracy'. The article clarifies the nature of this threat, and addresses two possible solutions (named, respectively, "resistance" and "accommodation"). It is argued that neither solution is likely to be successful, at least not without risking many other things we value about social decision-making. The result is a somewhat pessimistic conclusion in which we confront the possibility that we are creating decision-making processes that constrain and limit opportunities for human participation. Abstract Abstract Introduction

show abstract

Section: And Why Wouldn't We If We Are Promised Slimmer Waistlines mentioning

confidence: 99%

The Threat of Algocracy: Reality, Resistance and Accommodation

2016

View full text Add to dashboard Cite

show abstract

“…Doshi‐Velez and Kim () link interpretability to the need for an ML system to satisfy auxiliary criteria , i.e., criteria that are in part qualitative and cannot be satisfied by improved training (unlike, say, accuracy). While many examples are given by the authors (and others, e.g., Lipton, ) — including being nondiscriminatory (as in fairness), safety (Otte, ), and satisfying a user's right to explanation (as in Goodman & Flaxman, ) — there does not yet appear to be a comprehensive typology of these kinds of auxiliary criteria.…”

Section: Interpretability In Ml‐based Ai Systemsmentioning

confidence: 99%

Asking ‘Why’ in AI: Explainability of intelligent systems – perspectives and challenges

Preece

2018

Intell Sys Acc Fin Mgmt

118

View full text Add to dashboard Cite

Summary Recent rapid progress in machine learning (ML), particularly so‐called ‘deep learning’, has led to a resurgence in interest in explainability of artificial intelligence (AI) systems, reviving an area of research dating back to the 1970s. The aim of this article is to view current issues concerning ML‐based AI systems from the perspective of classical AI, showing that the fundamental problems are far from new, and arguing that elements of that earlier work offer routes to making progress towards explainable AI today.

show abstract

“…Some of the most successful ML methods, such as Artificial Neural Networks (ANN) and deep learning techniques, suffer from opaqueness of models, which cannot be interpreted by human experts and therefore cannot explain reasons for the outcomes they provide. This is a serious issue for ML adoption in all those sectors which require accountability of decisions and robustness of outputs against accidental or voluntary input manipulation [15,24]. Research efforts to build decipherable results of ML techniques and systems are therefore growing.…”

Section: Related Workmentioning

confidence: 99%

“…Research efforts to build decipherable results of ML techniques and systems are therefore growing. A conceptually simple approach is to exploit ensemble learning combining multiple lowdimensional submodels, where each individual submodel is simple enough to be verifiable by domain experts [24]. In [17] Bayesian learning was used to generate lists of rules in the if .…”

Section: Related Workmentioning

confidence: 99%

Machine learning in the Internet of Things: A semantic-enhanced approach

Ruta

Scioscia

Loseto

et al. 2018

View full text Add to dashboard Cite

New Internet of Things (IoT) applications and services more and more rely on an intelligent understanding of the environment from data gathered via heterogeneous sensors and micro-devices. Though increasingly effective, Machine Learning (ML) techniques generally do not go beyond classification of events with opaque labels, lacking meaningful representations and explanations of taxonomies. This paper proposes a framework for a semantic-enhanced data mining on sensor streams, amenable to resource-constrained pervasive contexts. It merges an ontology-based characterization of data distributions with non-standard reasoning for a fine-grained event detection by treating the typical classification problem of ML as a resource discovery. Outputs of classification are endowed with machine-understandable descriptions in standard Semantic Web languages, while explanation of matchmaking outcomes motivates confidence on results. A case study on road and traffic analysis allowed to validate the proposal and achieve an assessment with respect to state-of-the-art ML algorithms.

show abstract

Safe and Interpretable Machine Learning: A Methodological Review

Cited by 38 publications

References 9 publications

The Threat of Algocracy: Reality, Resistance and Accommodation

The Threat of Algocracy: Reality, Resistance and Accommodation

Asking ‘Why’ in AI: Explainability of intelligent systems – perspectives and challenges

Machine learning in the Internet of Things: A semantic-enhanced approach

Contact Info

Product

Resources

About