138 research outputs found
On Hybridizing Complete Bayesian Network Structure Search with Independence Tests
No full textBayesian Networks (BN) are probabilistic graphical models used to encode in a compact way a joint probability distribution over a set of random variables. The NP-complete problem of finding the most probable BN structure given the observed data has been largely studied in recent years. In the literature, several complete algorithms have been proposed for the problem; in parallel, several tests for statistical indepen- dence between the random variables have also been proposed, in order to reduce the size of the search space. In this work, we propose to hy- bridize the algorithm representing the state-of-the-art in complete search with two types of independence tests, and assess the performance of the hybrid algorithms in terms of both solution quality and computational time. Experimental results show that hybridization with both indepen- dence tests results in a substantial gain in computational time, against a limited loss in solution quality, and that none of the two independence tests consistently dominates the other in terms of computational time gain
Scale-free structure and topological properties in Reverse Engineering of Gene Regulatory Networks.
No full textBayesian Network structure learning: Hybridizing complete search with independence tests
No full textBayesian Networks (BN) are probabilistic graphical models used to encode in a compact way a joint probability distribution over a set of random variables. The NP-complete problem of finding the most probable BN structure given the observed data has been largely studied in recent years. In the literature, several complete algorithms have been proposed for the problem; in parallel, several tests for statistical independence between the random variables have been proposed, in order to reduce the size of the search space. In this work, we study how to hybridize the algorithm representing the state-of-the-art in complete search with two types of independence tests, and assess the performance of the two hybrid algorithms in terms of both solution quality and computational time. Experimental results show that hybridization with both types of independence test results in a substantial gain in computational time, against a limited loss in solution quality, and allow us to provide some guidelines on the choice of the test type, given the number of nodes in the network and the sample size
Towards a gendered innovation in AI
No full textIn this paper we address the problem of including the gender dimension in the content of Computer Science, notably in Artificial Intelligence (AI). We analyze first the fairness of Machine Learning (ML) algorithms from a gender point of view. Due to their nature of being bottom-up data-driven algorithms, the most common biases diffused in society about gender and ethnicity can be captured, subsumed and reinforced by them, as many ML applications show. Then, to understand how to develop a new gendered (Computer) Science and promote a gendered innovation in AI, we show a formal reflection on the scientific method utilized to produce innovation and a critical analysis of the logical rules underlying it
Fuzzy Mutual Information for Reverse Engineering of Gene Regulatory Networks
No full textThe aim of this work is to provide a new definition of Mutual Information using concepts from Fuzzy Sets theory. With this approach, we extended the model on which the well-known REVEAL algorithm for Reverse Engineering of gene regulatory networks is based and we designed a new flexible
version of it, called FuzzyReveal. The predictive power of our new version of the algorithm is promising, being comparable with a state-of-the-art algorithm on a set of simulated problems
Combining digital image correlation and virtual fields to design an optimized experimental setup for material identification
No full text
- …
