arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.03032cs.CY
收藏

通过众包逆向工程实现再生产:基于DeepMind Alpha Zero的神经网络案例研究

Reproducibility via Crowdsourced Reverse Engineering: A Neural Network Case Study With DeepMind's Alpha Zero

Dustin Tanksley, Donald C. Wunsch

摘要:

科学发现的可重复性是研究质量和完整性的重要标志。科学方法要求假设必须经过最关键的检验,并且独立试验的结果必须一致。因此,出版物应提供足够的信息,以便对其方法和声明进行客观评价。对于由公共资金支持的研究来说尤其如此,因为研究结果的透明度是公共投资的一种回报形式。不幸的是,由于各种原因,许多出版物没有达到这一标准,包括不可避免的原因,如知识产权保护和创建这些发现的实体的国家安全。这在医学研究和机器学习中是一个特别重要的问题。幸运的是,对于那些试图克服这些困难的人来说,互联网使分享实验变得更容易,并允许众包逆向工程。本文介绍了这种能力在神经网络研究的案例研究。对DeepMind的Alpha Zero的重要成就进行逆向工程的重大成功证明了通过共同努力重现结果可以实现的杠杆作用。

英文摘要:

The reproducibility of scientific findings are an important hallmark of quality and integrity in research. The scientific method requires hypotheses to be subjected to the most crucial tests, and for the results to be consistent across independent trials. Therefore, a publication is expected to provide sufficient information for an objective evaluation of its methods and claims. This is particularly true for research supported by public funds, where transparency of findings are a form of return on public investment. Unfortunately, many publications fall short of this mark for various reasons, including unavoidable ones such as intellectual property protection and national security of the entity creating those findings. This is a particularly important and documented problem in medical research, and in machine learning. Fortunately for those seeking to overcome these difficulties, the internet makes it easier to share experiments, and allows for crowd-sourced reverse engineering. A case study of this capability in neural networks research is presented in this paper. The significant success of reverse-engineering the important accomplishments of DeepMind's Alpha Zero exemplifies the leverage that can be achieved by a concerted effort to reproduce results.

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。

↑