Machine Learning (ML) is becoming increasingly important in daily life. In this context, Artificial Neural Networks (ANNs) are a popular approach within ML methods to realize an artificial intelligence. Usually, the topology of ANNs is predetermined. However, there are problems where it is difficult to find a suitable topology. Therefore, Topology and Weight Evolving Artificial Neural Network (TWEANN) algorithms have been developed that can find ANN topologies and weights using genetic algorithms. A well-known downside for large-scale problems is that TWEANN algorithms often evolve inefficient ANNs and require long runtimes. To address this issue, we propose a new TWEANN algorithm called Artificial Life Form (ALF) with the following technical advancements: (1) speciation via structural and semantic similarity to form better candidate solutions, (2) dynamic adaptation of the observed candidate solutions for better convergence properties, and (3) integration of solution quality into genetic reproduction to increase the probability of optimization success. Experiments on large-scale ML problems confirm that these approaches allow the fast solving of these problems and lead to efficient evolved ANNs.
翻译:机械学习(ML)在日常生活中正变得越来越重要。在这方面,人工神经网络(ANNS)是ML方法中实现人工智能的一种流行方法。通常,人为神经网络的地形学是先入为主的。然而,有些问题难以找到合适的地形学。因此,已经开发出地形学和微量演化的人工神经网络(TWEANN)算法,这些算法能够利用基因算法找到非非物质表层学和重量。大规模问题的一个众所周知的缺点是,TWEANN算法往往发展效率低下的非物质,需要长期时间。为了解决这个问题,我们建议采用称为人工生命表(ALF)的新的TWEANN算法,其技术进展如下:(1) 通过结构和语义相似性相似的外观来形成更好的候选解决办法,(2) 动态地调整观察到的候选解决办法,以增进趋同性,(3) 将解决办法质量纳入基因复制,以增加优化成功的可能性。在大规模ML问题上进行的实验证实,这些方法可以迅速解决这些问题,并导致高效率地演变。