arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.04634cs.NEcs.CVcs.LG
收藏

使用CoDeepNEAT和Keras的神经网络架构的神经进化

Neuroevolution of Neural Network Architectures Using CoDeepNEAT and Keras

Institute of Informatics(信息学研究所);Federal University of Rio Grande do Sul(南里奥格兰德联邦大学)

Jonas da Silveira Bohrer, Bruno Iochins Grisci, Marcio Dorn

摘要:

机器学习是计算机科学和统计学中的一个巨大的研究领域,致力于通过算法执行计算任务,这些算法不需要明确的指令,而是依赖于从数据样本中学习模式来自动推理。机器学习项目中涉及的大部分工作是定义解决给定问题的最佳算法类型。神经网络-尤其是深度神经网络-是该领域的主要解决方案类型。然而,网络本身可以根据为它们所做的架构选择产生非常不同的结果。为给定问题找到最佳网络拓扑和配置是一项挑战,由于需要考虑大量参数,因此需要领域知识和测试工作。这项工作的目的是提出一个适应性的实现一个完善的进化技术从神经进化领域,管理自动化的拓扑结构和超参数选择的任务。它使用一个流行的和可访问的机器学习框架- Keras -作为后端,展示结果和对原始算法的修改建议。该实现可在GitHub(https://github.com/sbcblab/Keras-CoDeepNEAT)上获得,其中包含文档和示例,以重现为此工作执行的实验。

英文摘要:

Machine learning is a huge field of study in computer science and statistics dedicated to the execution of computational tasks through algorithms that do not require explicit instructions but instead rely on learning patterns from data samples to automate inferences. A large portion of the work involved in a machine learning project is to define the best type of algorithm to solve a given problem. Neural networks - especially deep neural networks - are the predominant type of solution in the field. However, the networks themselves can produce very different results according to the architectural choices made for them. Finding the optimal network topology and configurations for a given problem is a challenge that requires domain knowledge and testing efforts due to a large number of parameters that need to be considered. The purpose of this work is to propose an adapted implementation of a well-established evolutionary technique from the neuroevolution field that manages to automate the tasks of topology and hyperparameter selection. It uses a popular and accessible machine learning framework - Keras - as the back-end, presenting results and proposed changes concerning the original algorithm. The implementation is available at GitHub (https://github.com/sbcblab/Keras-CoDeepNEAT) with documentation and examples to reproduce the experiments performed for this work.

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。

↑