1,721,624 research outputs found
Inductive querying for discovering subgroups and clusters
Full text linkWe introduce the problem of cluster-grouping and show that it integrates several important data mining tasks, i.e. subgroup discovery, mining correlated patterns and aspects from clustering. The problem of cluster-grouping can be regarded as a new type of inductive optimization query that asks for the k best patterns according to a convex criterion. The algorithm CG for solving cluster-grouping problems is presented and the underlying mechanisms are discussed. The approach is experimentally evaluated on a number of real-life data sets. The results indicate that the algorithm improves upon the subgroup discovery algorithm CN2-WRAcc and is competitive with the clustering algorithm Cob Web.status: Publishe
Towards Clausal Discovery for Stream Mining
Full text linkWith the increasing popularity of data streams it has become time to adapt logical and relational learning techniques for dealing with streams.
In this note, we present our preliminary results on upgrading the clausal discovery paradigm towards the mining of streams. In this setting, there is a stream of interpretations and the goal is to learn a clausal theory that is satisfied by these interpretations. Furthermore, in data streams the interpretations can be read (and processed) only once.sponsorship: This work was partially supported by the GOA project 08/008 on Probabilistic Logic Learning and the European Commission FP7 project BISON.status: Publishe
Individual fairness guarantees for neural networks
Full text linkWe consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs). In particular, we work with the epsilon-delta-IF formulation, which, given a NN and a similarity metric learnt from data, requires that the output difference between any pair of epsilon-similar individuals is bounded by a maximum decision tolerance delta >= 0. Working with a range of metrics, including the Mahalanobis distance, we propose a method to overapproximate the resulting optimisation problem using piecewise-linear functions to lower and upper bound the NN's non-linearities globally over the input space. We encode this computation as the solution of a Mixed-Integer Linear Programming problem and demonstrate that it can be used to compute IF guarantees on four datasets widely used for fairness benchmarking. We show how this formulation can be used to encourage models' fairness at training time by modifying the NN loss, and empirically confirm our approach yields NNs that are orders of magnitude fairer than state-of-the-art methods
Probabilistic logical sequence learning for video
Full text linkUnderstanding complex, dynamic scenes of real-world activities from low-level sensor data is of central importance for intelligent systems. The main difficulty lies in the fact that complex scenes are best described in high-level, logical formalisms, while sensor data usually consists of many low-level features. We first propose a method to obtain a logical representation of real-world, dynamic scenes based on input video stream solely. We focus on representing the video data using probabilistic relational sequences as a natural way to incorporate sensor uncertainty. They allow us to work with structured terms, and in addition they capture the inherent uncertainty of object detection. Further on, we employ r-grams as the probabilistic logical learning model for this application. In a first step we use r-grams in a simple setting and we show their viability in card games. We also show how r-grams can be upgraded to deal with uncertain observations.status: Publishe
Online Planning in POMDPs with Self-Improving Simulators
No full textHow can we plan efficiently in a large and complex environment when the time budget is limited? Given the original simulator of the environment, which may be computationally very demanding, we propose to learn online an approximate but much faster simulator that improves over time. To plan reliably and efficiently while the approximate simulator is learning, we develop a method that adaptively decides which simulator to use for every simulation, based on a statistic that measures the accuracy of the approximate simulator. This allows us to use the approximate simulator to replace the original simulator for faster simulations when it is accurate enough under the current context, thus trading off simulation speed and accuracy. Experimental results in two large domains show that when integrated with POMCP, our approach allows to plan with improving efficiency over time.Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Interactive Intelligenc
Frankenstein
No full text@inproceedings{orsini2015graph,
title={Graph invariant kernels},
author={Orsini, Francesco and Frasconi, Paolo and De Raedt, Luc},
booktitle={IJCAI Proceedings-International Joint Conference on Artificial Intelligence. IJCAI},
year={2015}
Learning constraint satisfaction problems: An ILP perspective
No full textWe investigate the problem of learning constraint satisfaction problems from an inductive logic programming perspective. Constraint satisfaction problems are the underlying basis for constraint programming and there is a long standing interest in techniques for learning these. Constraint satisfaction problems are often described using a relational logic, so inductive logic programming is a natural candidate for learning such problems. So far, there is however only little work on the intersection between learning constraint satisfaction problems and inductive logic programming. In this article, we point out several similarities and differences between the two classes of techniques that may inspire further cross-fertilization between these two fields.sponsorship: This work was supported by the European Commission under the project “Inductive Constraint Programming” (FP7- 284715).status: Publishe
- …
