NeuroEvolution automates the generation of Artificial Neural Networks through the application of techniques from Evolutionary Computation. The main goal of these approaches is to build models that maximize predictive performance, sometimes with an additional objective of minimizing computational complexity. Although the evolved models achieve competitive results performance-wise, their robustness to adversarial examples, which becomes a concern in security-critical scenarios, has received limited attention. In this paper, we evaluate the adversarial robustness of models found by two prominent NeuroEvolution approaches on the CIFAR-10 image classification task: DENSER and NSGA-Net. Since the models are publicly available, we consider white-box untargeted attacks, where the perturbations are bounded by either the L2 or the Linfinity-norm. Similarly to manually-designed networks, our results show that when the evolved models are attacked with iterative methods, their accuracy usually drops to, or close to, zero under both distance metrics. The DENSER model is an exception to this trend, showing some resistance under the L2 threat model, where its accuracy only drops from 93.70% to 18.10% even with iterative attacks. Additionally, we analyzed the impact of pre-processing applied to the data before the first layer of the network. Our observations suggest that some of these techniques can exacerbate the perturbations added to the original inputs, potentially harming robustness. Thus, this choice should not be neglected when automatically designing networks for applications where adversarial attacks are prone to occur.

This primer is an attempt to provide a detailed summary of the different facets of lifelong learning. We start with Chapter 2 which provides a high-level overview of lifelong learning systems. In this chapter, we discuss prominent scenarios in lifelong learning (Section 2.4), provide 8 Introduction a high-level organization of different lifelong learning approaches (Section 2.5), enumerate the desiderata for an ideal lifelong learning system (Section 2.6), discuss how lifelong learning is related to other learning paradigms (Section 2.7), describe common metrics used to evaluate lifelong learning systems (Section 2.8). This chapter is more useful for readers who are new to lifelong learning and want to get introduced to the field without focusing on specific approaches or benchmarks. The remaining chapters focus on specific aspects (either learning algorithms or benchmarks) and are more useful for readers who are looking for specific approaches or benchmarks. Chapter 3 focuses on regularization-based approaches that do not assume access to any data from previous tasks. Chapter 4 discusses memory-based approaches that typically use a replay buffer or an episodic memory to save subset of data across different tasks. Chapter 5 focuses on different architecture families (and their instantiations) that have been proposed for training lifelong learning systems. Following these different classes of learning algorithms, we discuss the commonly used evaluation benchmarks and metrics for lifelong learning (Chapter 6) and wrap up with a discussion of future challenges and important research directions in Chapter 7.

We present a comprehensive global sensitivity analysis of two single-objective and two multi-objective state-of-the-art global optimization evolutionary algorithms as an algorithm configuration problem. That is, we investigate the quality of influence hyperparameters have on the performance of algorithms in terms of their direct effect and interaction effect with other hyperparameters. Using three sensitivity analysis methods, Morris LHS, Morris, and Sobol, to systematically analyze tunable hyperparameters of covariance matrix adaptation evolutionary strategy, differential evolution, non-dominated sorting genetic algorithm III, and multi-objective evolutionary algorithm based on decomposition, the framework reveals the behaviors of hyperparameters to sampling methods and performance metrics. That is, it answers questions like what hyperparameters influence patterns, how they interact, how much they interact, and how much their direct influence is. Consequently, the ranking of hyperparameters suggests their order of tuning, and the pattern of influence reveals the stability of the algorithms.

Symbolic regression (SR) is the task of learning a model of data in the form of a mathematical expression. By their nature, SR models have the potential to be accurate and human-interpretable at the same time. Unfortunately, finding such models, i.e., performing SR, appears to be a computationally intensive task. Historically, SR has been tackled with heuristics such as greedy or genetic algorithms and, while some works have hinted at the possible hardness of SR, no proof has yet been given that SR is, in fact, NP-hard. This begs the question: Is there an exact polynomial-time algorithm to compute SR models? We provide evidence suggesting that the answer is probably negative by showing that SR is NP-hard.

PyGAD is an open-source Python library for building the genetic algorithm and optimizing machine learning algorithms. It works with Keras and PyTorch. PyGAD supports different types of crossover, mutation, and parent selection operators. PyGAD allows different types of problems to be optimized using the genetic algorithm by customizing the fitness function. Besides building the genetic algorithm, it builds and optimizes machine learning algorithms.

The particle swarm optimization (PSO) algorithm is a population-based search algorithm based on the simulation of the social behavior of birds within a flock. The initial intent of the particle swarm concept was to graphically simulate the graceful and unpredictable choreography of a bird flock, to discover patterns that govern the ability of birds to fly synchronously, and to suddenly change direction by regrouping in an optimal formation. From this initial objective, the concept evolved into a simple and efficient optimization algorithm. So, just like the Genetic Algorithm, PSO is inspired by nature. In PSO, individuals, also referred to as particles, are "flown" through hyperdimensional search space. Changes to the position of particles within the search space are based on the social-psychological tendency of individuals to emulate the success of other individuals.

This article presents new hexagonal and pentagonal PEM fuel cell models. The models have been optimized after achieving improved cell performance. The input parameters of the multi-objective optimization algorithm were pressure and temperature at the inlet, and consumption and output powers were the objective parameters. The output data of the numerical simulation has been trained using deep neural networks and then modeled with polynomial regression. The target functions have been extracted using the RSM (Response Surface Method), and the targets were optimized using the multi-objective genetic algorithm (NSGA-II). Compared to the base model, the optimized Pentagonal and Hexagonal models increase the output current density by 21.8% and 39.9%, respectively.

Due to the dynamics and uncertainty of the dynamic multi-objective optimization problems (DMOPs), it is difficult for algorithms to find a satisfactory solution set before the next environmental change, especially for some complex environments. One reason may be that the information in the environmental static stage can not be used well in the traditional framework. In this paper, a novel framework based on generational and environmental response strategies (FGERS) is proposed, in which response strategies are run both in the environmental change stage and the environmental static stage to obtain population evolution information of those both stages. Unlike in the traditional framework, response strategies are only run in the environmental change stage. For simplicity, the feed-forward center point strategy was chosen to be the response strategy in the novel dynamic framework (FGERS-CPS). FGERS-CPS is not only to predict change trend of the optimum solution set in the environmental change stage, but to predict the evolution trend of the population after several generations in the environmental static stage. Together with the feed-forward center point strategy, a simple memory strategy and adaptive diversity maintenance strategy were used to form the complete FGERS-CPS. On 13 DMOPs with various characteristics, FGERS-CPS was compared with four classical response strategies in the traditional framework. Experimental results show that FGERS-CPS is effective for DMOPs.

Zbigniew Michalewicz is Emeritus Professor of Computer Science at the University of Adelaide in Australia. He completed his Masters degree at Technical University of Warsaw in 1974 and he received Ph.D. degree from the Institute of Computer Science, Polish Academy of Sciences, in 1981. He also holds a Doctor of Science degree in Computer Science from the Polish Academy of Science. Zbigniew Michalewicz also holds Professor positions at the Institute of Computer Science, Polish Academy of Sciences, the Polish-Japanese Institute of Information Technology, and the State Key Laboratory of Software Engineering of Wuhan University, China. He is also associated with the Structural Complexity Laboratory at Seoul National University, South Korea.

Genetic Algorithms in Java Basics is a brief introduction to solving problems using genetic algorithms, with working projects and solutions written in the Java programming language. This brief book will guide you step-by-step through various implementations of genetic algorithms and some of their common applications, with the aim to give you a practical understanding allowing you to solve your own unique, individual problems. After reading this book you will be comfortable with the language specific issues and concepts involved with genetic algorithms and you'll have everything you need to start building your own.