1,721,016 research outputs found
Measuring the Feasibility of Analogical Transfer using Complexity
No full textFunding Information: The author wishes to thank the anonymous reviewers for their insightful comments and suggestions. Some of the presented ideas have been inspired by discussions with Antoine Cornuéjols, Jean-Louis Dessalles, Marie Al-Ghossein and Miguel Couceiro. This work was supported by the Academy of Finland Flagship programme: Finnish Center for Artificial Intelligence, FCAI. Publisher Copyright: © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).Analogies are 4-ary relations of the form “A is to B as C is to D". While focus has been mostly on how to solve an analogy, i.e. how to find correct values of D given A, B and C, less attention has been drawn on whether solving such an analogy was actually feasible. In this paper, we propose a quantification of the transferability of a source case (A and B) to solve a target problem C. This quantification is based on a complexity minimization principle which has been demonstrated to be efficient for solving analogies. We illustrate these notions on morphological analogies and show its connections with machine learning, and in particular with Unsupervised Domain Adaptation.Peer reviewe
Rethinking Collaborative Clustering: A Practical and Theoretical Study within the Realm of Multi-View Clustering
No full textInternational audienc
Going Beyond Counting First Authors in Author Co-citation Analysis
No full textThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Two-agent case-based reasoning for prediction
No full textDecision-making and prediction using Case-Based Reasoning involve two sequential steps: retrieval, where similar cases are selected, and adaptation, where these retrieved cases are used to infer a solution to the target problem. Traditionally, both steps are performed by a single agent, and prior research has emphasized the importance of adaptation-guided retrieval, i.e. considering the adaptation method when conducting retrieval. This paper explores an alternative setting, in which retrieval and adaptation are carried out by two distinct agents. A particularly relevant scenario arises when retrieval is performed by an AI agent, while adaptation is handled by a human. Since adaptation is conduced externally, adaptation-guided retrieval is only feasible if there is a model of how adaptation is performed. Two scenarios are examined: (1) when the retrieval agent knows the target solution and seeks to guide the adaptation toward it, and (2) when the retrieval agent does not have access to the target solution. Our approach is evaluated with a series of experiments on both a symbolic and a numerical task, using models of varying complexity. The results highlight the importance of inferring a correct model of the adaptation
Principe de minimum de complexité pour le transfert de connaissances en apprentissage artificiel
No full textClassical learning methods are often based on a simple but restrictive assumption: The present and future data are generated according to the same distributions. This hypothesis is particularly convenient when it comes to developing theoretical guarantees that the learning is accurate. However, it is not realistic from the point of view of applicative domains that have emerged in the last years.In this thesis, we focus on four distinct problems in artificial intelligence, that have mainly one common point: All of them imply knowledge transfer from one domain to the other. The first problem is analogical reasoning and concerns statements of the form "A is to B as C is to D". The second one is transfer learning and involves classification problem in situations where the training data and test data do not have the same distribution (nor even belong to the same space). The third one is data stream mining, ie. managing data that arrive one by one in a continuous and high-frequency stream with changes in the distributions. The last one is collaborative clustering and focuses on exchange of information between clustering algorithms to improve the quality of their predictions.The main contribution of this thesis is to present a general framework to deal with these transfer problems. This framework is based on the notion of Kolmogorov complexity, which measures the inner information of an object. This tool is particularly adapted to the problem of transfer, since it does not rely on probability distributions while being able to model the changes in the distributions.Apart from this modeling effort, we propose, in this thesis, various discussions on aspects and applications of the different problems of interest. These discussions all concern the possibility of transfer in multiple domains and are not based on complexity only.Les méthodes classiques d'apprentissage automatique reposent souvent sur une hypothèse simple mais restrictive: les données du passé et du présent sont générées selon une même distribution. Cette hypothèse permet de développer directement des garanties théoriques sur la précision de l'apprentissage. Cependant, elle n'est pas réaliste dans un grand nombre de domaines applicatifs qui ont émergé au cours des dernières années.Dans cette thèse, nous nous intéressons à quatre problèmes différents en intelligence artificielle, unis par un point commun: tous impliquent un transfer de connaissance d'un domaine vers un autre. Le premier problème est le raisonnement par analogie et s'intéresse à des assertions de la forme "A est à B ce que C est à D". Le second est l'apprentissage par transfert et se concentre sur des problèmes de classification dans des contextes où les données d'entraînement et de test ne sont pas de même distribution (ou n'appartiennent même pas au même espace). Le troisième est l'apprentissage sur flux de données, qui prend en compte des données apparaissant continument une à une à haute fréquence, avec des changements de distribution. Le dernier est le clustering collaboratif et consiste à faire échanger de l'information entre algorithmes de clusterings pour améliorer la qualité de leurs prédictions.La principale contribution de cette thèse est un cadre général pour traiter les problèmes de transfer. Ce cadre s'appuie sur la notion de complexité de Kolmogorov, qui mesure l'information continue dans un objet. Cet outil est particulièrement adapté au problème de transfert, du fait qu'il ne repose pas sur la notion de probabilité tout en étant capable de modéliser les changements de distributions.En plus de cet effort de modélisation, nous proposons dans cette thèse diverses discussions sur d'autres aspects ou applications de ces problèmes. Ces discussions s'articulent autour de la possibilité de transfert dans différents domaines et peuvent s'appuyer sur d'autres outils que la complexité
Variations on the Author
No full text“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
No full textWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
