ALF --一种用于进化大规模神经网络的基于适应度的人工生命形式
ALF -- A Fitness-Based Artificial Life Form for Evolving Large-Scale Neural Networks
摘要：
机器学习（ML）在日常生活中变得越来越重要。在这种情况下，人工神经网络（ANN）是ML方法中实现人工智能的流行方法。通常，人工神经网络的拓扑结构是预先确定的。然而，存在难以找到合适拓扑的问题。因此，拓扑和权重演化人工神经网络（TWEANN）算法已经被开发，其可以使用遗传算法来找到ANN拓扑和权重。大规模问题的一个众所周知的缺点是TWEANN算法通常会进化出低效的ANN，并且需要很长的运行时间。为了解决这个问题，我们提出了一种新的TWEANN算法，称为人工生命形式（ALF），具有以下技术进步：（1）通过结构和语义相似性形成更好的候选解决方案，（2）动态适应观察到的候选解决方案，以获得更好的收敛性能，以及（3）将解决方案质量集成到遗传繁殖中，以增加优化成功的概率。大规模ML问题的实验证实，这些方法可以快速解决这些问题，并导致有效的进化ANN。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
