Hugues Juillé

Learn More
Coevolutionary learning, which involves the embedding of adaptive learning agents in a tness environment that dynamically responds to their progress, is a potential solution for many technological chicken and egg problems. However, several impediments have to be overcome in order for coevolutionary learning to achieve continuous progress in the long term.(More)
We recently solved the two spirals problem, a di cult neural network benchmark classi cation problem, using the genetic programming primitives set up by [Koza, 1992]. Instead of using absolute tness, we use a relative tness based on a competition for coverage of the data set. This is a form of co-evolutionary search because the tness function changes with(More)
Complex systems composed of a large number of loosely coupled entities, with no central coordination offer a number of attractive properties like scalability, robustness or massively distributed computation. However, designing such complex systems presents some challenging issues that are difficult to tackle with traditional top-down engineering(More)
In the eld of optimization and machine learning techniques, some very eecient and promising tools like Genetic Algorithms (GAs) and Hill-Climbing have been designed. In this same eld, the Evolving Non-Determinism (END) model presented in this paper proposes an inventive way to explore the space of states that, using the simulated \incremental" co-evolution(More)
In the eld of Operation Research and Arti cial Intelligence, several stochastic search algorithms have been designed based on the theory of global random search (Zhigljavsky 1991). Basically, those techniques iteratively sample the search space with respect to a probability distribution which is updated according to the result of previous samples and some(More)
In this paper, we propose that learning complex behaviors can be achieved in a coevolutionary environment where one population consists of the human users of an interactive adaptive software tool and the “opposing” population is artificial, generated by a coevolutionary learning engine. We take advantage of the Internet, a connected community where people(More)
Representation of Information in Neural Networks A dissertation presented to the Faculty of the Graduate School of Arts and Sciences of Brandeis University, Waltham, Massachusetts by Ofer Melnik Arti cial neural networks are a computational paradigm inspired by neurobiology. As with any computational paradigm, its strengths are a direct result of how it(More)