Convolutional neural networks (CNNs) have gained remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For the most state-of-the-art CNNs, their architectures are often manually designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this article, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its “automatic” characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, compared to the state-of-the-art peer competitors covering eight manually designed CNNs, seven automatic + manually tuning, and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers, and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.

Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification

Humans rarely tackle every problem from scratch. Given this observation, the motivation for this paper is to improve optimization performance through adaptive knowledge transfer across related problems. The scope for spontaneous transfers under the simultaneous occurrence of multiple problems unveils the benefits of multitasking. Multitask optimization has recently demonstrated competence in solving multiple (related) optimization tasks concurrently. Notably, in the presence of underlying relationships between problems, the transfer of high-quality solutions across them has shown to facilitate superior performance characteristics. However, in the absence of any prior knowledge about the intertask synergies (as is often the case with general black-box optimization), the threat of predominantly negative transfer prevails. Susceptibility to negative intertask interactions can impede the overall convergence behavior. To allay such fears, in this paper, we propose a novel evolutionary computation framework that enables online learning and exploitation of the similarities (and discrepancies) between distinct tasks in multitask settings, for an enhanced optimization process. Our proposal is based on the principled theoretical arguments that seek to minimize the tendency of harmful interactions between tasks, based on a purely data-driven learning of relationships among them. The efficacy of our proposed method is validated experimentally on a series of synthetic benchmarks, as well as a practical study that provides insights into the behavior of the method in the face of several tasks occurring at once.

Multifactorial Evolutionary Algorithm With Online Transfer Parameter Estimation: MFEA-II

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 of ...

/pdf/a-survey-on-evolutionary-machine-learning-41xxfv2woy.pdf

A survey on evolutionary machine learning

An online-learning-based evolutionary many-objective algorithm

The evolutionary algorithm (EA) is a nature-inspired population-based search method that works on Darwinian principles of natural selection. Due to its strong search capability and simplicity of implementation, EA has been successfully applied to solve many complex optimization problems, which cannot be easily solved by traditional exact mathematical approaches, such as linear programming, quadratic programming, and convex optimization. Despite its great success, it is worth noting that traditional EA solvers start the search from scratch by assuming zero prior knowledge about the task at hand. However, as problems seldom exist in isolation, solving one problem may yield useful information for solving other related problems. There has been growing interest in conducting research on evolutionary transfer optimization (ETO) in recent years: a paradigm that integrates EA solvers with knowledge learning and transfer across related domains to achieve better optimization efficiency and performance. This paper provides an overview of existing works of ETO based on the type of problems being solved by these methods, which are ETO for Optimization in Uncertain Environment, ETO for Multitask Optimization, ETO for Complex Optimization, ETO for Multi/Many-Objective Optimization, and ETO for Machine Learning Applications. The paper also highlights some of the challenges faced in this emerging research field of computational intelligence and discusses some promising future research directions in ETO. It is hoped that the study presented in this paper can help to inspire the development of more advanced ETO methods and applications.

Evolutionary Transfer Optimization - A New Frontier in Evolutionary Computation Research

One of the major distinguishing features of the dynamic multiobjective optimization problems (DMOPs) is the optimization objectives will change over time, thus tracking the varying Pareto-optimal front becomes a challenge. One of the promising solutions is reusing the "experiences" to construct a prediction model via statistical machine learning approaches. However most of the existing methods ignore the non-independent and identically distributed nature of data used to construct the prediction model. In this paper, we propose an algorithmic framework, called Tr-DMOEA, which integrates transfer learning and population-based evolutionary algorithm for solving the DMOPs. This approach takes the transfer learning method as a tool to help reuse the past experience for speeding up the evolutionary process, and at the same time, any population based multiobjective algorithms can benefit from this integration without any extensive modifications. To verify this, we incorporate the proposed approach into the development of three well-known algorithms, nondominated sorting genetic algorithm II (NSGA-II), multiobjective particle swarm optimization (MOPSO), and the regularity model-based multiobjective estimation of distribution algorithm (RM-MEDA), and then employ twelve benchmark functions to test these algorithms as well as compare with some chosen state-of-the-art designs. The experimental results confirm the effectiveness of the proposed method through exploiting machine learning technology.

Transfer Learning based Dynamic Multiobjective Optimization Algorithms

One of the major distinguishing features of the dynamic multiobjective optimization problems (DMOPs) is that optimization objectives will change over time, thus tracking the varying Pareto-optimal front becomes a challenge. One of the promising solutions is reusing “experiences” to construct a prediction model via statistical machine learning approaches. However, most existing methods neglect the nonindependent and identically distributed nature of data to construct the prediction model. In this paper, we propose an algorithmic framework, called transfer learning-based dynamic multiobjective evolutionary algorithm (EA), which integrates transfer learning and population-based EAs to solve the DMOPs. This approach exploits the transfer learning technique as a tool to generate an effective initial population pool via reusing past experience to speed up the evolutionary process, and at the same time any population-based multiobjective algorithms can benefit from this integration without any extensive modifications. To verify this idea, we incorporate the proposed approach into the development of three well-known EAs, nondominated sorting genetic algorithm II, multiobjective particle swarm optimization, and the regularity model-based multiobjective estimation of distribution algorithm. We employ 12 benchmark functions to test these algorithms as well as compare them with some chosen state-of-the-art designs. The experimental results confirm the effectiveness of the proposed design for DMOPs.

Transfer Learning-Based Dynamic Multiobjective Optimization Algorithms

Many real-world optimization problems involve multiple objectives, constraints, and parameters that may change over time. These problems are often called dynamic multiobjective optimization problems (DMOPs). The difficulty in solving DMOPs is the need to track the changing Pareto-optimal front efficiently and accurately. It is known that transfer learning (TL)-based methods have the advantage of reusing experiences obtained from past computational processes to improve the quality of current solutions. However, existing TL-based methods are generally computationally intensive and thus time consuming. This article proposes a new memory-driven manifold TL-based evolutionary algorithm for dynamic multiobjective optimization (MMTL-DMOEA). The method combines the mechanism of memory to preserve the best individuals from the past with the feature of manifold TL to predict the optimal individuals at the new instance during the evolution. The elites of these individuals obtained from both past experience and future prediction will then constitute as the initial population in the optimization process. This strategy significantly improves the quality of solutions at the initial stage and reduces the computational cost required in existing methods. Different benchmark problems are used to validate the proposed algorithm and the simulation results are compared with state-of-the-art dynamic multiobjective optimization algorithms (DMOAs). The results show that our approach is capable of improving the computational speed by two orders of magnitude while achieving a better quality of solutions than existing methods.

A Fast Dynamic Evolutionary Multiobjective Algorithm via Manifold Transfer Learning

Dynamic Multi-objective Estimation of Distribution Algorithm based on Domain Adaptation and Nonparametric Estimation

Dynamic Multi-objective Optimization Problems (DMOPs) refer to optimization problems that objective functions will change with time. Solving DMOPs implies that the Pareto Optimal Set (POS) at different moments can be accurately found, and this is a very difficult job due to the dynamics of the optimization problems. The POS that have been obtained in the past can help us to find the POS of the next time more quickly and accurately. Therefore, in this paper we present a Support Vector Machine (SVM) based Dynamic Multi-Objective Evolutionary optimization Algorithm, called SVM-DMOEA. The algorithm uses the POS that has been obtained to train a SVM and then take the trained SVM to classify the solutions of the dynamic optimization problem at the next moment, and thus it is able to generate an initial population which consists of different individuals recognized by the trained SVM. The initial populuation can be fed into any population based optimization algorithm, e.g., the Nondominated Sorting Genetic Algorithm II (NSGA-II), to get the POS at that moment. The experimental results show the validity of our proposed approach.

Liming Qiu

Papers

Transfer Learning based Dynamic Multiobjective Optimization Algorithms

Transfer Learning-Based Dynamic Multiobjective Optimization Algorithms

A Fast Dynamic Evolutionary Multiobjective Algorithm via Manifold Transfer Learning

Dynamic Multi-objective Estimation of Distribution Algorithm based on Domain Adaptation and Nonparametric Estimation

Solving dynamic multi-objective optimization problems via support vector machine