Feature selection is an important task in data mining and machine learning to reduce the dimensionality of increase performance algorithm, such as a classification algorithm. However, feature challenging due mainly large search space. A variety methods have been applied solve problems, where evolutionary computation (EC) techniques recently gained much attention shown some success. there are no comprehensive guidelines on strengths weaknesses alternative approaches. This leads disjointed...

Classification problems often have a large number of features in the data sets, but not all them are useful for classification. Irrelevant and redundant may even reduce performance. Feature selection aims to choose small relevant achieve similar or better classification performance than using features. It has two main conflicting objectives maximizing minimizing However, most existing feature algorithms treat task as single objective problem. This paper presents first study on...

Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For most state-of-the-art CNNs, architectures are often manually-designed with expertise both and investigated problems. Therefore, it is difficult for users, who no extended to design optimal CNN own problems interest. In this paper, we propose an automatic architecture method by using genetic...

Evolutionary paradigms have been successfully applied to neural network designs for two decades. Unfortunately, these methods cannot scale well the modern deep networks due complicated architectures and large quantities of connection weights. In this paper, we propose a new method using genetic algorithms evolving weight initialization values convolutional address image classification problems. proposed algorithm, an efficient variable-length gene encoding strategy is designed represent...

The problem of domain generalization is to take knowledge acquired from a number related domains, where training data available, and then successfully apply it previously unseen domains. We propose new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good performance for cross-domain object recognition. algorithm extends the standard denoising autoencoder framework by substituting artificially induced corruption with naturally occurring inter-domain variability in...

This paper addresses classification tasks on a particular target domain in which labeled training data are only available from source domains different (but related to) the target. Two closely frameworks, adaptation and generalization, concerned with such tasks, where difference between those frameworks is availability of unlabeled data: can leverage information, while generalization cannot. We propose Scatter Component Analyis (SCA), fast representation learning algorithm that be applied to...

Deep Neural Networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role their performance, which is usually manually designed with rich expertise. However, such design process labour intensive because the trial-and-error process, and also not easy to realize due rare expertise practice. Architecture Search (NAS) type technology that can automatically. Among different methods NAS, Evolutionary Computation (EC) recently gained much attention...

The performance of convolutional neural networks (CNNs) highly relies on their architectures. In order to design a CNN with promising performance, extensive expertise in both CNNs and the investigated problem domain is required, which not necessarily available every interested user. To address this problem, we propose automatically evolve architectures by using genetic algorithm (GA) based ResNet DenseNet blocks. proposed completely automatic designing particular, neither preprocessing...

In classification, machine learning algorithms can suffer a performance bias when data sets are unbalanced. Data unbalanced at least one class is represented by only small number of training examples (called the minority class), while other class(es) make up majority. this scenario, classifiers have good accuracy on majority class, but very poor class(es). This paper proposes multiobjective genetic programming (MOGP) approach to evolving accurate and diverse ensembles program with both...

With a global search mechanism, particle swarm optimization (PSO) has shown promise in feature selection (FS). However, most of the current PSO-based FS methods use fix-length representation, which is inflexible and limits performance PSO for FS. When applying these to high-dimensional data, it not only consumes significant amount memory but also requires high computational cost. Overcoming this limitation enables work on data with much higher dimensionality become more popular advance...

A scheduling policy strongly influences the performance of a manufacturing system. However, design an effective is complicated and time consuming due to complexity each decision, as well interactions among these decisions. This paper develops four new multi-objective genetic programming-based hyperheuristic (MO-GPHH) methods for automatic policies, including dispatching rules due-date assignment in job shop environments. In addition using three existing search strategies, nondominated...

Genetic programming has been a powerful technique for automated design of production scheduling heuristics. Many studies have shown that heuristics evolved by genetic can outperform many existing manually designed in the literature. The flexibility also allows it to discover very sophisticated deal with complex and dynamic environments. However, as compared other applications or evolutionary computation techniques, configurations requirements are more complicated. In this paper, unified...

Convolutional neural networks (CNNs) have shown remarkable performance in various real-world applications. Unfortunately, the promising of CNNs can be achieved only when their architectures are optimally constructed. The state-of-the-art typically handcrafted with extensive expertise both and investigated data, which consequently hampers widespread adoption for less experienced users. Evolutionary deep learning (EDL) is able to automatically design best CNN without much expertise. However,...

Artificial intelligence (AI) emphasises the creation of intelligent machines/systems that function like humans. AI has been applied to many real-world applications. Machine learning is a branch based on idea systems can learn from data, identify hidden patterns, and make decisions with little/minimal human intervention. Evolutionary computation an umbrella population-based intelligent/learning algorithms inspired by nature, where New Zealand good international reputation. This paper provides...

Dynamic flexible job-shop scheduling (DFJSS) is a challenging combinational optimization problem that takes the dynamic environment into account. Genetic programming hyperheuristics (GPHH) have been widely used to evolve heuristics for scheduling. A proper selection of terminal set critical factor success GPHH. However, there wide range features can capture different characteristics state. Moreover, importance feature unclear from one scenario another. The irrelevant and redundant may lead...

In machine learning, discretization and feature selection (FS) are important techniques for preprocessing data to improve the performance of an algorithm on high-dimensional data. Since many FS methods require discrete data, a common practice is apply before FS. addition, sake efficiency, features usually discretized individually (or univariate). This scheme works based assumption that each independently influences task, which may not hold in cases where interactions exist. Therefore,...

Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but best architecture a CNN specific problem can be extremely complicated and hard design. This paper focuses on utilising Particle Swarm Optimisation (PSO) automatically search for optimal CNNs without any manual work involved. In order achieve goal, three improvements made based traditional PSO. First, novel encoding strategy inspired by computer which empowers...

Dynamic flexible job shop scheduling (JSS) is an important combinatorial optimization problem with complex routing and sequencing decisions under dynamic environments. Genetic programming (GP), as a hyperheuristic approach, has been successfully applied to evolve heuristics for JSS. However, its training process time consuming, it faces the retraining once characteristics of scenarios vary. It known that multitask learning promising paradigm solving multiple tasks simultaneously by sharing...