• Publications
  • Influence
A Survey of Methods for Explaining Black Box Models
In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes bothExpand
  • 953
  • 75
  • PDF
Local Rule-Based Explanations of Black Box Decision Systems
TLDR
In this paper we focus on the problem of black box outcome explanation, i.e., explaining the reasons of the decision taken on a specific instance. Expand
  • 116
  • 7
  • PDF
Factual and Counterfactual Explanations for Black Box Decision Making
TLDR
The rise of sophisticated machine learning models has brought accurate but obscure decision systems, which hide their logic, thus undermining transparency, trust, and the adoption of artificial intelligence in socially sensitive and safety-critical contexts. Expand
  • 31
  • 3
MyWay: Location prediction via mobility profiling
TLDR
We propose MyWay, a prediction system which exploits the individual systematic behaviors modeled by mobility profiles to predict human movements. Expand
  • 48
  • 2
Black Box Explanation by Learning Image Exemplars in the Latent Feature Space
TLDR
We present an approach to explain the decisions of black box models for image classification by exploiting the latent feature space learned through an adversarial autoencoder. Expand
  • 20
  • 2
  • PDF
Open the Black Box Data-Driven Explanation of Black Box Decision Systems
TLDR
We introduce the local-to-global framework for black box explanation, a novel approach with promising early results, which paves the road for a wide spectrum of future developments along three dimensions: (i) the language for expressing explanations in terms of highly expressive logic-based rules, with a statistical and causal interpretation; (ii) the inference of local explanations aimed at revealing the logic of the decision adopted for a specific instance by querying and auditing the black box. Expand
  • 17
  • 2
  • PDF
Meaningful Explanations of Black Box AI Decision Systems
TLDR
We introduce the local-toglobal framework for black box explanation, articulated along three lines: (i) the language for expressing explanations in terms of logic rules, with statistical and causal interpretation; (ii) the inference of local explanations for revealing the decision rationale for a specific case, by auditing the black box in the vicinity of the target instance; (iii), the bottom-up generalization of many local explanations into simple global ones, with algorithms that optimize for quality and comprehensibility. Expand
  • 44
  • 1
The AI Black Box Explanation Problem
  • 3
  • 1
Next Basket Prediction using Recurring Sequential Patterns
TLDR
We propose the Temporal Annotated Recurring Sequences (TARS ), adaptive patterns which model the purchasing behavior of an individual by four main characteristics: co-occurency, sequentiality, periodicity and recurrency. Expand
  • 6
  • 1
  • PDF
“ Are we playing like Music-Stars ? ” Placing Emerging Artists on the Italian Music Scene
The Italian emerging bands chase success on the footprint of popular artists by playing rhythmic danceable and happy songs. Our finding comes out from a study of the Italian music scene and how theExpand
  • 5
  • 1
  • PDF
...
1
2
3
4
5
...