增量进化与深度人工神经网络的发展
Incremental Evolution and Development of Deep Artificial Neural Networks
摘要：
已知神经进化（NE）方法用于将演化计算应用于人工神经网络（ANN）的优化。尽管帮助非专家用户设计和训练ANN，但绝大多数NE方法忽略了在解决其他任务时收集的知识，即，对于每个问题，进化都是从零开始的，最终延缓了进化过程。为了克服这个缺点，我们将快速深度进化网络结构化表示（Fast-DENSER）扩展到增量开发。我们假设，通过转移从以前的任务中获得的知识，我们可以获得更好的结果和加速进化。结果表明，增量开发所生成的模型的平均性能在统计上优于非增量开发的平均性能。如果增量开发所执行的评估数量小于非增量开发所执行的评估数量，则所获得的结果在性能上相似，这表明增量开发加速了进化。最后，使用增量开发生成的模型更好地泛化，因此，无需进一步进化，就可以在看不见的问题上报告卓越的性能。
英文摘要：
NeuroEvolution (NE) methods are known for applying Evolutionary Computation to the optimisation of Artificial Neural Networks(ANNs). Despite aiding non-expert users to design and train ANNs, the vast majority of NE approaches disregard the knowledge that is gathered when solving other tasks, i.e., evolution starts from scratch for each problem, ultimately delaying the evolutionary process. To overcome this drawback, we extend Fast Deep Evolutionary Network Structured Representation (Fast-DENSER) to incremental development. We hypothesise that by transferring the knowledge gained from previous tasks we can attain superior results and speedup evolution. The results show that the average performance of the models generated by incremental development is statistically superior to the non-incremental average performance. In case the number of evaluations performed by incremental development is smaller than the performed by non-incremental development the attained results are similar in performance, which indicates that incremental development speeds up evolution. Lastly, the models generated using incremental development generalise better, and thus, without further evolution, report a superior performance on unseen problems.
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。
