Ramon López de Mántaras

Retrieval, reuse, revision and retention in case-based reasoning

Case-based reasoning (CBR) is an approach to problem solving that emphasizes the role of prior experience during future problem solving (i.e., new problems are solved by reusing and if necessary adapting the solutions to similar problems that were solved in the past). It has enjoyed considerable success in a wide variety of problem solving tasks and domains. Following a brief overview of the traditional problem-solving cycle in CBR, we examine the cognitive science foundations of CBR and its relationship to analogical reasoning. We then review a representative selection of CBR research in the past few decades on aspects of retrieval, reuse, revision and retention.

SaxEx: a case-based reasoning system for generating expressive musical performances

Abstract The problem of generating expressive musical performances in the context of tenor saxophone interpretations was studied. Several recordings of a tenor sax playing different Jazz ballads with different degrees of expressiveness including an inexpressive interpretation of each ballad were made. These recordings were analyzed, using Sms spectral modeling techniques, to extract information related to several expressive parameters. This set of parameters and the scores constitute the set of cases (examples) of a case‐based system. From this set of cases, the system infers a set of possible expressive transformations for a given new phrase applying similarity criteria, based on background musical knowledge, between this new phrase and the set of cases. Finally, SaxEx applies the inferred expressive transformations to the new phrase using the synthesis capabilities of Sms.

Fuzzy set modelling in case-based reasoning

This paper is an attempt at providing a fuzzy set formalization of case‐based reasoning and decision. Learning aspects are not considered here. The proposed approach assumes a principle stating that “the more similar are the problem description attributes, the more similar are the outcome attributes.” A weaker form of this principle concluding only on the graded possibility of the similarity of the outcome attributes, is also considered. These two forms of the case‐based reasoning principle are modelled in terms of fuzzy rules. Then an approximate reasoning machinery taking advantage of this principle enables us to apply the information stored in the memory of previous cases to the current problem. A particular instance of case‐based reasoning, named case‐based decision, is especially investigated. A logical formalization of the basic case‐based reasoning inference is also proposed. Extensions of the proposed approach in order to handle imprecise or fuzzy descriptions or to manage more general forms of the principle underlying case‐based reasoning are briefly discussed in the conclusion.

Machine Learning: ECML 2000

Overfitting is often considered the central problem in machine learning and data mining. When good performance on training data is not enough to reliably predict good generalization, researchers and practitioners often invoke ”Occam’s razor” to select among hypotheses: prefer the simplest hypothesis consistent with the data. Occam’s razor has a long history in science, but a mass of recent evidence suggests that in most cases it is outperformed by methods that deliberately produce more complex models. The poor performance of Occam’s razor can be largely traced to its failure to account for the search process by which hypotheses are obtained: by effectively assuming that the hypothesis space is exhaustively searched, complexity-based methods tend to over-penalize large spaces. This talk describes how information about the search process can be taken into account when evaluating hypotheses. The expected generalization error of a hypothesis is computed as a function of the search steps leading to it. Two variations of this ”processoriented” approach have yielded significant improvements in the accuracy of a rule learner. Process-oriented evaluation leads to the seemingly paradoxical conclusion that the same hypothesis will have different expected generalization errors depending on how it was generated. I believe that this is as it should be, and that a corresponding shift in our way of thinking about inductive learning is required.

A case-based approach for coordinated action selection in robot soccer

Designing coordinated robot behaviors in uncertain, dynamic, real-time, adversarial environments, such as in robot soccer, is very challenging. In this work we present a case-based reasoning approach for cooperative action selection, which relies on the storage, retrieval, and adaptation of example cases. We focus on cases of coordinated attacking passes between robots in the presence of the defending opponent robots. We present the case representation explicitly distinguishing between controllable and uncontrollable indexing features, corresponding to the positions of the team members and opponent robots, respectively. We use the symmetric properties of the domain to automatically augment the case library. We introduce a retrieval technique that weights the similarity of a situation in terms of the continuous ball positional features, the uncontrollable features, and the cost of moving the robots from the current situation to match the case controllable features. The case adaptation includes a best match between the positions of the robots in the past case and in the new situation. The robots are assigned an adapted position to which they move to maximize the match to the retrieved case. Case retrieval and reuse are achieved within the distributed team of robots through communication and sharing of own internal states and actions. We evaluate our approach, both in simulation and with real robots, in laboratory scenarios with two attacking robots versus two defending robots as well as versus a defender and a goalie. We show that we achieve the desired coordinated passing behavior, and also outperform a reactive action selection approach.

Machine learning from examples: inductive and lazy methods

Machine Learning from examples may be used, within Artificial Intelligence, as a way to acquire general knowledge or associate to a concrete problem solving system. Inductive learning methods are typically used to acquire general knowledge from examples. Lazy methods are those in which the experience is accessed, selected and used in a problem-centered way. In this paper we report important approaches to inductive learning methods such as propositional and relational learners, with an emphasis in Inductive Logic Programming based methods, as well as to lazy methods such as instance-based and case-based reasoning.

Qualitative reasoning with imprecise probabilities

This paper investigates the possibility of performing automated reasoning in probabilistic knowledge bases when probabilities are expressed by means of linguistic quantifiers. Data are expressed in terms of ill-known conditional probabilities represented by linguistic terms. Each linguistic term is expressed as a prescribed interval of proportions. Then instead of propagating numbers, qualitative terms are propagated in accordance with the numerical interpretation of these terms. The quantified syllogism, modeling the chaining of probabilistic rules, is studied in this context. It is shown that a qualitative counterpart of this syllogism makes sense and is fairly independent of the thresholds defining the linguistically meaningful intervals, provided that these threshold values remain in accordance with the intuition. The inference power is less than a full-fledged probabilistic constraint propagation device but corresponds better to what could be thought of as commonsense probabilistic reasoning. Suggestions that may improve the inferencing power in the qualitative setting are proposed.

Robust bayesian linear classifier ensembles

Ensemble classifiers combine the classification results of several classifiers. Simple ensemble methods such as uniform averaging over a set of models usually provide an improvement over selecting the single best model. Usually probabilistic classifiers restrict the set of possible models that can be learnt in order to lower computational complexity costs. In these restricted spaces, where incorrect modeling assumptions are possibly made, uniform averaging sometimes performs even better than bayesian model averaging. Linear mixtures over sets of models provide an space that includes uniform averaging as a particular case. We develop two algorithms for learning maximum a posteriori weights for linear mixtures, based on expectation maximization and on constrained optimizition. We provide a nontrivial example of the utility of these two algorithms by applying them for one dependence estimators. We develop the conjugate distribution for one dependence estimators and empirically show that uniform averaging is clearly superior to Bayesian model averaging for this family of models. After that we empirically show that the maximum a posteriori linear mixture weights improve accuracy significantly over uniform aggregation.

Fast and robust object segmentation with the Integral Linear Classifier

We propose an efficient method, built on the popular Bag of Features approach, that obtains robust multiclass pixellevel object segmentation of an image in less than 500ms, with results comparable or better than most state of the art methods. We introduce the Integral Linear Classifier (ILC), that can readily obtain the classification score for any image sub-window with only 6 additions and 1 product by fusing the accumulation and classification steps in a single operation. In order to design a method as efficient as possible, our building blocks are carefully selected from the quickest in the state of the art. More precisely, we evaluate the performance of three popular local descriptors, that can be very efficiently computed using integral images, and two fast quantization methods: the Hierarchical K-Means, and the Extremely Randomized Forest. Finally, we explore the utility of adding spatial bins to the Bag of Features histograms and that of cascade classifiers to improve the obtained segmentation. Our method is compared to the state of the art in the difficult Graz-02 and PASCAL 2007 Segmentation Challenge datasets.

An Interactive Case-Based Reasoning Approach for Generating Expressive Music

In this paper we present an extension of an existing system, called SaxEx, capable of generating expressive musical performances based on Case-Based Reasoning (CBR) techniques. The previous version of SaxEx used pre-fixed criteria within the different CBR steps and, therefore, there was no room for user interaction. This paper discusses the necessity of user interaction during the CBR process and how this decision enhances the capabilities and the usability of the system. The set of evaluation experiments conducted show the advantages of SaxExs new interactive functionality, particularly for future educational applications of the system.