Domenico Maisto

Biological invasion-inspired migration in distributed evolutionary algorithms

Migration strategy plays an important role in designing effective distributed evolutionary algorithms. In this work, a novel migration model inspired to the phenomenon known as biological invasion is devised. The migration strategy is implemented through a multistage process involving invading subpopulations and their competition with native individuals. Such a general approach is used within a stepping-stone parallel model adopting Differential Evolution as the local algorithm. The resulting distributed algorithm is evaluated on a wide set of classical test functions against a large number of sequential and other distributed versions of Differential Evolution available in literature. The findings show that, in most of the cases, the proposed algorithm is able to achieve better performance in terms of both solution quality and convergence rate.

Satellite Image Registration by Distributed Differential Evolution

In this paper a parallel software system based on Differential Evolution for the registration of images is designed, implemented and tested on a set of 2---D remotely sensed images on two problems, i.e. mosaicking and changes in time. Registration is carried out by finding the most suitable affine transformation in terms of maximization of the mutual information between the first image and the transformation of the second one, without any need for setting control points. A coarse---grained distributed version is implemented on a cluster of personal computers.

Distributed Differential Evolution for the Registration of Remotely Sensed Images

This paper deals with the design and implementation of a parallel software system based on differential evolution for the registration of images, and with its testing on two bidimensional remotely sensed images on mosaicking problem. Registration is carried out by finding the most suitable affine transformation in terms of maximization of the mutual information between the first image and the transformation of the second one, without any need for setting control points. A coarse-grained distributed version is implemented on a cluster of personal computers

An adaptive invasion-based model for distributed Differential Evolution

A novel adaptive model for a recently devised distributed Differential Evolution algorithm is introduced. The distributed algorithm, following the stepping-stone model, is characterized by a migration model inspired by the phenomenon known as biological invasion. The adaptive model is endowed with three updating schemes to randomly set the mutation and the crossover parameters. These schemes are here tied to the migration and are guided by a performance measure between two consecutive migrations. The proposed adaptive model is tested on a set of classical benchmark functions over the different setting schemes. To evaluate its performance, the model is compared against the original non-adaptive version with a fixed parameter setting, and against a well-known distributed Differential Evolution algorithm equipped with the same schemes for the control parameter updating. The experimental study shows that the method results in high effectiveness in terms of solutions detected and convergence speed on most of the benchmark problems and for the majority of the setting schemes investigated. Finally, to further estimate its effectiveness, the proposed approach is also compared with several state-of-the-art Differential Evolution frameworks endowed with different randomized or self-adaptive parameter setting strategies. This comparison shows that our adaptive model allows obtaining the best performance in most of the tests studied.

Problem Solving as Probabilistic Inference with Subgoaling: Explaining Human Successes and Pitfalls in the Tower of Hanoi

How do humans and other animals face novel problems for which predefined solutions are not available? Human problem solving links to flexible reasoning and inference rather than to slow trial-and-error learning. It has received considerable attention since the early days of cognitive science, giving rise to well known cognitive architectures such as SOAR and ACT-R, but its computational and brain mechanisms remain incompletely known. Furthermore, it is still unclear whether problem solving is a “specialized” domain or module of cognition, in the sense that it requires computations that are fundamentally different from those supporting perception and action systems. Here we advance a novel view of human problem solving as probabilistic inference with subgoaling. In this perspective, key insights from cognitive architectures are retained such as the importance of using subgoals to split problems into subproblems. However, here the underlying computations use probabilistic inference methods analogous to those that are increasingly popular in the study of perception and action systems. To test our model we focus on the widely used Tower of Hanoi (ToH) task, and show that our proposed method can reproduce characteristic idiosyncrasies of human problem solvers: their sensitivity to the “community structure” of the ToH and their difficulties in executing so-called “counterintuitive” movements. Our analysis reveals that subgoals have two key roles in probabilistic inference and problem solving. First, prior beliefs on (likely) useful subgoals carve the problem space and define an implicit metric for the problem at hand—a metric to which humans are sensitive. Second, subgoals are used as waypoints in the probabilistic problem solving inference and permit to find effective solutions that, when unavailable, lead to problem solving deficits. Our study thus suggests that a probabilistic inference scheme enhanced with subgoals provides a comprehensive framework to study problem solving and its deficits.

Divide et impera: subgoaling reduces the complexity of probabilistic inference and problem solving.

It has long been recognized that humans (and possibly other animals) usually break problems down into smaller and more manageable problems using subgoals. Despite a general consensus that subgoaling helps problem solving, it is still unclear what the mechanisms guiding online subgoal selection are during the solution of novel problems for which predefined solutions are not available. Under which conditions does subgoaling lead to optimal behaviour? When is subgoaling better than solving a problem from start to finish? Which is the best number and sequence of subgoals to solve a given problem? How are these subgoals selected during online inference? Here, we present a computational account of subgoaling in problem solving. Following Occams razor, we propose that good subgoals are those that permit planning solutions and controlling behaviour using less information resources, thus yielding parsimony in inference and control. We implement this principle using approximate probabilistic inference: subgoals are selected using a sampling method that considers the descriptive complexity of the resulting sub-problems. We validate the proposed method using a standard reinforcement learning benchmark (four-rooms scenario) and show that the proposed method requires less inferential steps and permits selecting more compact control programs compared to an equivalent procedure without subgoaling. Furthermore, we show that the proposed method offers a mechanistic explanation of the neuronal dynamics found in the prefrontal cortex of monkeys that solve planning problems. Our computational framework provides a novel integrative perspective on subgoaling and its adaptive advantages for planning, control and learning, such as for example lowering cognitive effort and working memory load.

A Multiobjective Extremal Optimization Algorithm for Efficient Mapping in Grids

Extremal Optimization is proposed to map the tasks making up a user application in grid environments. To comply at the same time with minimal use of grid resources and maximal hardware reliability, a multiobjective version based on the concept of Pareto dominance is developed. The proposed mapper is tested on eight different experiments representing a suitable set of typical real-time situations.

A Quantum-inspired Evolutionary Algorithm with a competitive variation operator for Multiple-Fault Diagnosis

A heuristic search algorithm, the Quantum-inspired Competitive Evolutionary Algorithm (QuCEA), based on both quantum and evolutionary computing, is proposed. The individuals of a population, coded as qubit strings, evolve by means of an original variation operator inspired by competitive learning. The proposed operator is application independent and intuitively controllable by a single real parameter. QuCEA has been applied to Multiple-Fault Diagnosis, a typical NP-hard problem for industrial diagnosis. In particular, the proposed algorithm gives remarkable results both in simulation and in on-field tests for a lift monitoring system, also in comparison with a standard genetic algorithm and a state-of-the-art Quantum-inspired Evolutionary Algorithm.

Nonparametric Problem-Space Clustering: Learning Efficient Codes for Cognitive Control Tasks

We present an information-theoretic method permitting one to find structure in a problem space (here, in a spatial navigation domain) and cluster it in ways that are convenient to solve different classes of control problems, which include planning a path to a goal from a known or an unknown location, achieving multiple goals and exploring a novel environment. Our generative nonparametric approach, called the generative embedded Chinese restaurant process (geCRP), extends the family of Chinese restaurant process (CRP) models by introducing a parameterizable notion of distance (or kernel) between the states to be clustered together. By using different kernels, such as the the conditional probability or joint probability of two states, the same geCRP method clusters the environment in ways that are more sensitive to different control-related information, such as goal, sub-goal and path information. We perform a series of simulations in three scenarios—an open space, a grid world with four rooms and a maze having the same structure as the Hanoi Tower—in order to illustrate the characteristics of the different clusters (obtained using different kernels) and their relative benefits for solving planning and control problems.

Parsimony doesn't mean simplicity: genetic programming for inductive inference on noisy data

A Genetic Programming algorithm based on Solomonoffs probabilistic induction is designed and used to face an Inductive Inference task, i.e., symbolic regression. To this aim, some test functions are dressed with increasing levels of noise and the algorithm is employed to denoise the resulting function and recover the starting functions. Then, the algorithm is compared against a classical parsimony-based GP. The results shows the superiority of the Solomonoff-based approach.