Automatic Manifold identification in large datasets is currently a challenging problem in Machine Learning. This process consists on separating a large dataset blindly, according to the form defined by the data instances in the space. Data is ...

Current robust optimisation techniques can be divided into two main groups: algorithms that rely on previously sampled points versus those that need additional function evaluations to confirm robustness of solutions during optimisation. This paper first ...

Genetic programming (GP) is widely used for constructing models with applications in control, classification, regression, etc.; however, it has some shortcomings, such as generalization. This paper proposes to enhance the GP generalization by ...

Computing the Pareto Set (PS) of optimal cloud schedules in terms of cost and makespan for a given application and set of cloud instance types is NP-complete. Moreover, cloud instances' volatility requires fast PS recomputations. While genetic ...

Generating networks that satisfy a given set of constraints can be very challenging, especially when the metrics being controlled for are not very prescriptive and the networks could potentially exhibit very different higher-order structure within those ...

The aim of this paper is to estimate the extent of social specialization of residential space within the French Riviera metropolitan area. Unlike classical approaches, where social groups are pre-defined through given characteristics of households, our ...

Restricted Boltzmann Machines (RBMs) are amongst the most widely pursued techniques in deep learning-based environments. However, the problem of selecting a suitable set of parameters still remains an open question, since it is not straightforward to ...

Genetic Programming based hyper-heuristics (GP-HH) for dynamic job shop scheduling (JSS) problems are approaches which aim to address the issue where heuristics are only effective for specific JSS problem domains, and that designing effective heuristics ...

Class imbalance is a problem that commonly affects 'real world' classification datasets, and has been shown to hinder the performance of classifiers. A dataset suffers from class imbalance when the number of instances belonging to one class outnumbers ...

Auxiliary objectives may be used to reduce number of iterations of an evolutionary algorithm (EA). The corresponding approach is called multi-objectivization.

We consider two multi-objectivization methods: EA+RL and MOEA+RL, where MOEA is a multi-...

Substitution Boxes (S-boxes) play an important role in many modern-day cryptography algorithms. Indeed, without carefully chosen S-boxes many ciphers would be easy to break. The design of suitable S-boxes attracts a lot of attention in cryptography ...

We integrate a Denoising Autoencoder (DAE) into an Estimation of Distribution Algorithm (EDA) and evaluate the performance of DAE-EDA on several combinatorial optimization problems. We asses the number of fitness evaluations and the required CPU times. ...

We argue against the usage of known finite benchmarks to compare the performance of swarm and evolutionary methods. The key of our criticism is that these methods support a huge set of parameter values and available sub-steps which can be selected and ...

This paper investigates the frequently observed phenomenon of stagnation which appears on particle swarm optimization (PSO). We introduce a measure of significance of single dimensions and provide experimental and theoretical evidence that the classical ...

It is well-known that faults affecting an electronic device may compromise its correct functionality, and industries have to check that their devices are fault-free before selling them. In case of a processor core, this task may be accomplished by ...

ParamILS is a sophisticated tuning method able to provide valuable information for designers and manage conditional parameters. EvoCa is a recently proposed tuner which does not require a fine definition of the initial parameters values. In this work, ...

This paper proposes a two-step ants algorithm for the Multidimensional Knapsack Problem. In the first step, the algorithm uses an Anti-pheromone to detect which objects are less suitable to be part of a near-optimal solution solving the opposite ...

This paper presents a comparison of two Evolutionary Artificial Neural Network (EANN) variants acting as the autonomous control system for instances of the θ-Consensus Avoidance Problem (θ-CAP). A novel variant of EANN is proposed by adopting ...

We present a novel diversity method named Grid Diversity Operator (GDO) that can be incorporated into multiple population-based optimization algorithms that guides the containing algorithm in creating new individuals in sparsely visited areas of the ...

In this paper we propose an extension of the NM-landscape to model multi-objective problems (MOPs). We illustrate the link between the introduced model and previous landscapes used to study MOPs. Empirical results are presented for a variety of ...

In this paper we propose a discrete algebraic-based Differential Evolution for the Linear Ordering Problem (LOP). The search space of LOP is composed by permutations of objects, thus it is possible to use some group theoretical concepts and methods. ...

This article presents an evolutionary algorithm for optimizing the offensive behavior of opposing units in the real-time strategy game StarCraft II. Encounters between different unit groups are examined and described. The goal for each group is to deal ...

The momentum parameter is common within numerous optimization and local search algorithms, particularly in the popular back propagation neural network learning algorithm. Computationally cheap and prevalent in gradient descent approaches, it is not ...

A previously described hyper-heuristic framework named NELLI is adapted for the classic Job Shop Scheduling Problem (JSSP) and used to find ensembles of reusable heuristics that cooperate to cover the heuristic search space. A new heuristic generator is ...

Pyramidal Neural Networks (PNN) are computational systems inspired in the concept of receptive fields from the human visual system. In the original approach, the size of the receptive field within the same 2D layer is constant. However, their size is ...

This paper presents a hybrid Particle Swarm Optimization (PSO) for solving Vehicle Routing Problem with Time Windows (VRPTW). Three versions of the algorithm were implemented. The first version is a traditional PSO. In this case, the initialization is ...

A genetic algorithm adjusts parameters of image segmentation techniques to be transposed from manually annotated cropped images to perform on the complete contour-blank histopathological pictures.

This paper presents an characteristic analysis of multi-funnel functions for expensive optimization scenario. IPOP-CMA-ES is applied to three multi-funnel functions from the BBOB benchmarks for two different budget scenarios. The experimental analysis ...

The performance of cooperative co-evolutionary algorithms for large-scale global optimization (LSGO) can be significantly affected by the adopted problem decomposition. This study investigates a new adaptive Cooperative Coevolutionary algorithm in which ...

Artificial Immune Systems (AIS), one of the promising artificial intelligence methods, has been widely adopted in the optimization domain. However, their application to many-objective domain is rather scattered. In this respect, we extend the AIS-based ...

Recurrent Cartesian Genetic Programming is a recently proposed extension to Cartesian Genetic Programming which allows cyclic program structures to be evolved. We apply both standard and Recurrent Cartesian Genetic Programming to the domain of series ...

We used a meta-optimization environment to compare two reference versions of the Particle Swarm Optimization (PSO) algorithm, namely Standard PSO 2006 and Standard PSO 2011, on the CEC 2013 benchmark. We first compared the performances of the two ...

An urban environment provides a number of challenges and opportunities for organisations faced with the task of scheduling a mobile workforce. Given a mixed set of public and private transportation and a list of scheduling constraints, we seek to find ...

Circuit approximation has been developed in recent years as a viable method for constructing energy efficient electronic systems. An open problem is how to effectively obtain approximate circuits showing good compromises between key circuit parameters --...

Maritime data uniquely challenges imagery analysis. Such data suffers from degradation, limited samples, and varied formats. To this end, the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach is investigated in addressing such ...

Crossover is an important genetic operator that can combine beneficial genes together. Unfortunately, neuro-evolution (NE) has not experienced the benefits of crossover, despite significant efforts that enabled crossover for neural networks. ...

In general, multi-objective optimization problems (MOPs) with up to three objectives can be solved using multi-objecti-ve evolutionary algorithms (MOEAs). However, for MOPs with four or more objectives, current algorithms show some limitations. To ...

Crowdsourcing is a well-known method in which intelligence tasks are completed by an anonymous group of human participants. These are tasks that cannot yet be adequately performed by computers. Rather than performing an intelligence task outright, one ...

Portfolio optimization problems are challenging as they contain different kinds of constrains and their complexity becomes very high when the number of assets grows. In this paper, we develop a dimension-decreasing particle swarm optimization (DDPSO) ...

We present a population genetic algorithm which satisfies detailed balance, and which has a stationary distribution that factorises into an explicit form for arbitrary fitness functions. For a population size of 1, it is the Metropolis algorithm with a `...

This paper presents a genetic algorithm (GA) software system for solving the container vessel stowage problem. The problem is a NP-hard problem with multiple and complex restrictions. The approach is based on a two-phase procedure, one for master ...

We develop previous work by Cazenave applying Monte Carlo Tree Search (MCTS) to programming. We compare MCTS to Genetic Programming (GP) and find that MCTS is competitive with GP for standard benchmarks.

The field of presentation of Extended Classifier System(XCS) has undergone many fluctuations and shifts over the years to adapt different domain problems. With the increasing usage of application of artificial intelligence requirements for more ...

The Pareto Concavity Elimination Transformation (PaCcET) is a promising new development in multi-objective optimization. It transforms the objective space so that a computationally-cheap linear combination of objectives can attain (even concave) Pareto-...

Genetic Programming has been very successful in solving a large area of problems but its use as a machine learning algorithm has been limited so far. One of the reasons is the problem of overfitting which cannot be solved or suppresed as easily as in ...