http://popups.lib.uliege.be/1373-5411/index.php?id=4026 Index terms fr 0 http://popups.lib.uliege.be/1373-5411/index.php?id=1646 The architecture, Complexity and Organized Behaviour Within Environmental Bounds (COBWEB), was developed to support an anticipatory approach to adaptation. COBWEB consists of a large number of autonomous agents, each a genetic algorithm, using different strategies to adapt to changing resource availability. Anticipatory genetic algorithms, that are Turing complete, as well as mutation are used to allow the agents to respond to a changing environment. The simulation has four attractors, which exhibit sensitivity to initial conditions, and the spatial patterns of the agents exhibit wide variation as well as local structure, which might indicate adapive or anticipatory behaviour Mon, 15 Jul 2024 16:15:28 +0200 Tue, 08 Oct 2024 14:35:57 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=1646 http://popups.lib.uliege.be/1373-5411/index.php?id=643 Many analogies found in natural systems give evidence that the role of noise in a complex system might well lead to further organization. So, noise seems a good way in order to create novelty or to test the strength of algorithms. In this paper, we are going to analyse some artificial learning mechanisms such as genetic algorithms or neural networks, which may be generally formulated as an optimization problem by specifying a performance criterion, and then by using the simple but powerful technique of stochastic hill-climbing along the gradient. In these algorithms, the integration of random is a good way to maintain the exploration property during searching, useful for avoiding local optima or when environment is dynamic. We claim that artificial learning must overcome their limitations using the expedient of random search. This is due to attractors always present inside search procedures. We discuss in order to find another way to create order without having any presupposed attractors. This is also a central question for anticipatory systems which must learn about themselves and their environment. Fri, 28 Jun 2024 16:01:34 +0200 Tue, 08 Oct 2024 14:07:42 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=643 http://popups.lib.uliege.be/1373-5411/index.php?id=3572 The robotic inverse kinematic problem can be rightly classified as a very felt theme in the field of robotics. Many studies have been carried out in order to find new methods for the solution of the problem as alternatives to the traditional ones. In particular, every method able to improve the calculation speed is more and more appreciated. In the present paper an innovative method for the numerical inversion of non linear equations sets is shown. The approach is based on some procedures typical of the soft-computing area. In particular, the inverse kinematic problem is solved by a Neural Network optimised by means of a Genetic Algorithm acting inside an Hyperincursive scheme. After the introduction of the methodology developed, the paper shows some results obtained on a SCARA robot; they appear very good in terms of computational speed, even if the solution precision is not high near the boundaries of the working area. Thu, 26 Sep 2024 10:01:39 +0200 Tue, 08 Oct 2024 14:03:45 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=3572 http://popups.lib.uliege.be/1373-5411/index.php?id=1601 We discuss the use of genetic algorithms (GAs) for the generation of music. We explain the structure of a typical GA, and outline existing work on the use of GAs in computer music. We propose that the addition of domain-specific knowledge can enhance the quality and speed of production of GA results, and describe two systems which exemplify this. However, we conclude that GAs are not ideal for the simulation of human musical thought (notwithstanding their ability to produce good results) because their operation in no way simulates human behaviour. Mon, 15 Jul 2024 15:35:41 +0200 Mon, 07 Oct 2024 15:50:11 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=1601 http://popups.lib.uliege.be/1373-5411/index.php?id=797 Recent trends in multi-agent ITS can be split in a movement away from the traditional ITS architecture consisting of modules (i.e., the expert, student, and instructional modules) and a movement towards looking at the process (i.e., planning, monitoring, and diagnosing). The strong idea as a core assumption for this second approach is that the term "cognitive agent" can be described as an agent that learns in the same way as people learns. So, focus is put both on learning protocols and mutant processes within a new paradigm for cognitive agents: the Systemion (Systemic Daemon). Systemions are designed as agents that powerfully increase their knowledge by learning from other and agents that assume their survival by joining two unique properties of the living systems: replication and evolution. Life cycle in systemions is self-controlled by two concurrent mechanisms - first, a reproduction system, continuously modified by a learning algorithm, is used to fertilize the cloning of a "child" agent into a given lineage; - second, selective genetic algorithms act as a mutant processes to create new fathers of an improved lineage. Mon, 01 Jul 2024 13:58:13 +0200 Mon, 07 Oct 2024 13:09:38 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=797