Computer Science

Since the scale factor and the crossover rate significantly influence the performance of differential evolution (DE), parameter adaptation methods (PAMs) for the two parameters have been well studied in the DE community. Although PAMs can sufficiently improve the effectiveness of DE, PAMs are poorly understood (e.g., the working principle of PAMs). One of the difficulties in understanding PAMs comes from the unclarity of the parameter space that consists of the scale factor and the crossover rate. This paper addresses this issue by analyzing adaptive parameter landscapes in PAMs for DE. First, we propose a concept of an adaptive parameter landscape, which captures a moment in a parameter adaptation process. For each iteration, each individual in the population has its adaptive parameter landscape. Second, we propose a method of analyzing adaptive parameter landscapes using a 1-step-lookahead greedy improvement metric. Third, we examine adaptive parameter landscapes in PAMs by using the proposed method. Results provide insightful information about PAMs in DE.

Distributed coevolutionary Generative Adversarial Network (GAN) training has empirically shown success in overcoming GAN training pathologies. This is mainly due to diversity maintenance in the populations of generators and discriminators during the training process. The method studied here coevolves sub-populations on each cell of a spatial grid organized into overlapping Moore neighborhoods. We investigate the impact on the performance of two algorithm components that influence the diversity during coevolution: the performance-based selection/replacement inside each sub-population and the communication through migration of solutions (networks) among overlapping neighborhoods. In experiments on MNIST dataset, we find that the combination of these two components provides the best generative models. In addition, migrating solutions without applying selection in the sub-populations achieves competitive results, while selection without communication between cells reduces performance.

In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach progressively simplifies the original search space by dropping unpromising candidates, thus can reduce difficulties for existing NAS methods to find superior architectures. In particular, we propose an angle-based metric to guide the shrinking process. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed metric is more stable and accurate than accuracy-based and magnitude-based metrics to predict the capability of child models. We also show that the angle-based metric can converge fast while training supernet, enabling us to get promising shrunk search spaces efficiently. ABS can easily apply to most of NAS approaches (e.g. SPOS, FairNAS, ProxylessNAS, DARTS and PDARTS). Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.

In this paper, we introduce a new evolutionary optimization algorithm based on Tukey's symmetric lambda distribution. Tukey distribution is defined by 3 parameters, the shape parameter, the scale parameter, and the location parameter or average value. Various other distributions can be approximated by changing the shape parameter, and as a result can encompass a large class of probability distributions. In addition, Because of these attributes, an Evolutionary Programming (EP) algorithm with Tukey mutation operator may perform well in a large class of optimization problems. Various schemes in implementation of EP with Tukey distribution are discussed, and the resulting algorithms are applied to selected test functions and antenna design problems.

With the onset of Electric vehicles, and them becoming more and more popular, autonomous cars are the future in the travel/driving experience. The barrier to reaching level 5 autonomy is the difficulty in the collection of data that incorporates good driving habits and the lack thereof. The problem with current implementations of self-driving cars is the need for massively large datasets and the need to evaluate the driving in the dataset. We propose a system that requires no data for its training. An evolutionary model would have the capability to optimize itself towards the fitness function. We have implemented Neuroevolution, a form of genetic algorithm, to train/evolve self-driving cars in a simulated virtual environment with the help of Unreal Engine 4, which utilizes Nvidia's PhysX Physics Engine to portray real-world vehicle dynamics accurately. We were able to observe the serendipitous nature of evolution and have exploited it to reach our optimal solution. We also demonstrate the ease in generalizing attributes brought about by genetic algorithms and how they may be used as a boilerplate upon which other machine learning techniques may be used to improve the overall driving experience.

Individual-based models are complex and they have usually an elevated number of input parameters which must be tuned for reproducing the observed population data or the experimental results as accurately as possible. Thus, one of the weakest points of this modelling approach lies on the fact that rarely the modeler has the enough information about the correct values or even the acceptable range for the input parameters. Consequently, several parameter combinations must be tried to find an acceptable set of input factors minimizing the deviations of simulated and the reference dataset. In practice, most of times, it is computationally unfeasible to traverse the complete search space trying all every possible combination to find the best of set of parameters. That is precisely an instance of a combinatorial problem which is suitable for being solved by metaheuristics and evolutionary computation techniques. In this work, we introduce EvoPER, an R package for simplifying the parameter estimation using evolutionary computation methods.

We algorithmically construct a two hidden layer feedforward neural network (TLFN) model with the weights fixed as the unit coordinate vectors of the d -dimensional Euclidean space and having 3d+2 number of hidden neurons in total, which can approximate any continuous d -variable function with an arbitrary precision. This result, in particular, shows an advantage of the TLFN model over the single hidden layer feedforward neural network (SLFN) model, since SLFNs with fixed weights do not have the capability of approximating multivariate functions.

Deep neural networks power most recent successes of artificial intelligence, spanning from self-driving cars to computer aided diagnosis in radiology and pathology. The high-stake data intensive process of surgery could highly benefit from such computational methods. However, surgeons and computer scientists should partner to develop and assess deep learning applications of value to patients and healthcare systems. This chapter and the accompanying hands-on material were designed for surgeons willing to understand the intuitions behind neural networks, become familiar with deep learning concepts and tasks, grasp what implementing a deep learning model in surgery means, and finally appreciate the specific challenges and limitations of deep neural networks in surgery. For the associated hands-on material, please see this https URL.

The understanding and acceptance of evolution by natural selection has become a difficult issue in many parts of the world, particularly the United States of America. The use of games to improve intuition about evolution via natural selection is promising but can be challenging. We propose the use of modifications to commercial games using artificial life techniques to 'stealth teach' about evolution via natural selection, provide a proof-of-concept mod of the game Stardew Valley, and report on its initial reception.

This paper examines the use of artificial neural network approach in identifying the origin of clove buds based on metabolites composition. Generally, large data sets are critical for accurate identification. Machine learning with large data sets lead to precise identification based on origins. However, clove buds uses small data sets due to lack of metabolites composition and their high cost of extraction. The results show that backpropagation and resilient propagation with one and two hidden layers identifies clove buds origin accurately. The backpropagation with one hidden layer offers 99.91% and 99.47% for training and testing data sets, respectively. The resilient propagation with two hidden layers offers 99.96% and 97.89% accuracy for training and testing data sets, respectively.