For the learning phase, Levinson used a combination of rote learning as in case-based reasoning, restructuring to derive significant generalizations, a similarity measure based on the generalizations, and a method of back propagation to estimate the value of any case that occurred in a game. For playing chess, the cases were board positions represented as graphs. Every position that occurred in a game was stored in a generalization hierarchy, such as those used in definitional networks. At the end of each game, the system used back propagation to adjust the estimated values of each position that led to the win, loss, or draw. When playing a game, the system would examine all legal moves from a given position, search for similar positions in the hierarchy, and choose the move that led to a position whose closest match had the best predicted value.

The department's research in Machine Learning contributes to the state-of-the-art of individual methods and algorithms as well as combinations of methods targeting particular tasks, for example, combining data-intensive methods with knowledge-based methods to produce user explanations for decision support. Our strongest contributions to the international research front until now have been within Bayesian learning and probabilistic reasoning, evolutionary learning and neural networks, and instance-based learning and case-based reasoning. In addition, we have ongoing activities at a high international level within large-scale data and information management. Over the last years there has been an increased interest in combined methods, e.g.

A content vector, that is an array of values that represents the information content suitable for the Vector space model matching, as explained in 4.; with paired justifications (They express the provenience of that element, if from initial interview or the current active stereotype, or feedback, etc.) Moreover, changes to the User Model are regulated using a fixed hierarchy, so that lower items in the hierarchy cannot overwrite the values set by higher items. For example an element modified by the user feedback is not affected by changes from the stereotypes, etc. Contexts are initializated all the same for every user that has a non-zero value in her/his user model content vector for each cluster having one or more non-null contexts. Then these contexts are copied in the user's model and evolves indipendently according to the single user history. A set of user keywords each weighted with a value representing its actual importance for the user.

In just few years, case-based reasoning has evolved from a research topic studied at a small number of specialized academic labs into an industrial-strength technology applied in various fields. The INRECA methodology presented in detail in this monograph provides a data analysis framework for developing case-based reasoning solutions for successful applications in real-world industrial contexts. The book provides a self-contained introduction to case-based reasoning applications that address both R&D professionals and general IT managers interested in this powerful new technology. In this second edition, improvements and updates have been incorporated throughout the text. Particularly useful is the systematic coverage of experience factory applications at various steps; and, of course, the references have been extended substantially.

Interested in the research on machine learning and time-series analysis algorithms able to process big data in an efficient, adaptive, and robust way. Currently focused on their application to Cognitive Stimulation and Rehabilitation (see Innobrain and Cognitio projects) and Autism Spectrum Disorders (see AMATE project). Another topic of my interest is the use of Machine Learning techniques to reason and learn about musical processes like expressive music generation. Currently focused on the study of musical expressivity in Nylon Guitars (see guitarLab) and social tools for music education (see PRAISE). We have studied the issue of expressiveness in the context of tenor saxophon interpretations (see Saxex and TempoExpress systems) in collaboration with the Music Technology Group (UPF).

Next year's ICCBR conference has been announced!

Personalized recommendation of products, documents, and collaborators has become an important way of meeting user needs in commerce, information provision, and community services, whether on the web, through mobile interfaces, or through traditional desktop interfaces. This tutorial first reviews the types of personalized recommendation that are being used commercially and in research systems. It then systematically presents and compares the underlying AI techniques, including recent variants and extensions of collaborative filtering, demographic and case-based approaches, and decision-theoretic methods. The properties of the various techniques will be compared within a general framework, so that participants learn how to match recommendation techniques to applications and how to combine complementary techniques.

Current research projects include projects to investigate the use of multiple case representation and indexing schemes in precedent-based CBR, the effect of high level reasoning goals on supporting CBR tasks and vice versa in a mixed paradigm blackboard-based architecture, the use of CBR for generation of retrieval strategies in the context of information retrieval, and the automatic selection of parameters for dynamic scheduling problems.

We need heuristics for the intentional reminding of explanation patterns XP retrieval is the process of formulating questions to memory: we characterize an anomalous situation in terms of a set of indices, and ask what XPs in memory explain similar situations. When no answer is available, we must reformulate the question into one that we can answer. When no solution is directly available, people often fall back on asking standard questions that give background information. Answers to explanation questions like what physical causes underlie this event?, what special circumstances made the event happen now?, what motivates the actor of this surprising action?, how did the victim enable this bad event?, or what groups might the actor be trying to serve?, may suggest relevant factors that can be used as indices for XP retrieval. Though the XPs accessed in this way might not be directly applicable, it may be possible to adapt them. A creative system needs a set of explanation questions for gathering information, rules for selecting which questions to apply in a given situation, and rules for transforming them to fit.

One of life's harsh little truths is that there are unfortunately a lot of people living unfulfilling lives. There are so many twists and turns that make us deviate from our hopes and dreams, leading to an awful lot of compromise. It's impossible to just flip a switch and have it all change to whatever we're dreaming of, but there at least a few ways to finally take the reigns and hopefully chase down a little more fulfillment and happiness. One of our favorite resources for this is The 67 Steps by Tai Lopez. If you want to know more about it then The 67 Steps Rocks!