-
Explaining Image Classifiers Generating Exemplars and Counter-Exemplars from ...
We present an approach to explain the decisions of black-box image classifiers through synthetic exemplar and counter-exemplar learnt in the latent feature space. Our...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
Explaining Sentiment Classification with Synthetic Exemplars and Counter-Exem...
We present xspells, a model-agnostic local approach for explaining the decisions of a black box model for sentiment classification of short texts. The explanations provided...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
Multi layered Explanations from Algorithmic Impact Assessments in the GDPR
Impact assessments have received particular attention on both sides of the Atlantic as a tool for implementing algorithmic accountability. The aim of this paper is to address... -
Explanation of Deep Models with Limited Interaction for Trade Secret and Priv...
An ever-increasing number of decisions affecting our lives are made by algorithms. For this reason, algorithmic transparency is becoming a pressing need: automated decisions... -
Explaining Any Time Series Classifier
We present a method to explain the decisions of black box models for time series classification. The explanation consists of factual and counterfactual shapelet-based rules...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
Interpretable Next Basket Prediction Boosted with Representative Recipes
Food is an essential element of our lives, cultures, and a crucial part of human experience. The study of food purchases can drive the design of practical services such as...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
Heterogeneous Document Embeddings for Cross-Lingual Text Classification
Funnelling (Fun) is a method for cross-lingual text classification (CLC) based on a two-tier ensemble for heterogeneous transfer learning. In Fun, 1st-tier classifiers, each...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
A comparative study of fairness enhancing interventions in machine learning
Computers are increasingly used to make decisions that have significant impact on people's lives. Often, these predictions can affect different population subgroups... -
Machine Learning Explainability Through Comprehensible Decision Trees
The role of decisions made by machine learning algorithms in our lives is ever increasing. In reaction to this phenomenon, the European General Data Protection Regulation... -
Interpretable socioeconomic status inference from aerial imagery through urba...
Urbanization is a great challenge for modern societies, promising better access to economic opportunities, but widening socioeconomic inequalities. Accurately tracking this...-
HTML
The resource: 'Link to Publication' is not accessible as guest user. You must login to access it!
-
HTML
-
Algorithmic decision making and the cost of fairness
Algorithms are now regularly used to decide whether defendants awaiting trial are too dangerous to be released back into the community. In some cases, black defendants are... -
Bias in algorithmic filtering and personalization
Online information intermediaries such as Facebook and Google are slowly replacing traditional media channels thereby partly becoming the gatekeepers of our society. To deal... -
Accountability for the Use of Algorithms in a Big Data Environment
Accountability is the ability to provide good reasons in order to explain and to justify actions, decisions, and policies for a (hypothetical) forum of persons or... -
Algorithmic Accountability and Public Reason
The ever-increasing application of algorithms to decision-making in a range of social contexts has prompted demands for algorithmic accountability. Accountable decision-makers... -
Introduction to Data science for Social Scientists
This course, initially designed for social scientists, covers several topics of data science. Python programming Data Cleaning and Transformation Classification Clustering...-
ipynb
The resource: 'Python Basics' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Python Basics - Exercise' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Data Manipulation in Pandas' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Data Manipulation in ...' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Case Study: Titanic data ...' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Clustering' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Case study: Titanic Clustering' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Classification' is not accessible as guest user. You must login to access it!
-
ipynb
The resource: 'Case study: Titanic ...' is not accessible as guest user. You must login to access it!
-
HTML
The resource: 'Titanic Dataset' is not accessible as guest user. You must login to access it!
-
ipynb
-
Can Big Data Bridge Gaps in Migration Statistics
Traditional statistical data on international migration suffers from the problems (gaps) of inconsistency in definitions, differences in geographical coverages, absence of...-
HTML
The resource: '"Can Big Data Bridge Gaps ...' is not accessible as guest user. You must login to access it!
-
HTML
-
A qualitative exploration of perceptions of algorithmic fairness
Algorithmic systems increasingly shape information people are exposed to as well as influence decisions about employment, finances, and other opportunities. In some cases,... -
AI and Big Data A blueprint for a human rights and social and ethical impact ...
Building on studies of the collective dimension of data protection, this article sets out to embed this new perspective in an assessment model centred on human rights (Human... -
European Data Governance Act
The proposal for a Regulation of the European Parliament and of the Council on data governance is the first of a set of measures announced in the 2020 European strategy for...-
HTML
The resource: 'html' is not accessible as guest user. You must login to access it!
-
HTML
-
On Artificial Intelligence - A European approach to excellence and trust
Artificial Intelligence is developing fast. It will change our lives by improving healthcare (e.g. making diagnosis more precise, enabling better prevention of diseases),...-
HTML
The resource: 'html' is not accessible as guest user. You must login to access it!
-
HTML