arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.08351astro-ph.COgr-qc
收藏

利用可解释机器学习增强宇宙学模型选择

Enhancing Cosmological Model Selection with Interpretable Machine Learning

Indira Ocampo, George Alestas, Savvas Nesseris, Domenico Sapone

AI总结:

提出基于神经网络和 LIME 可解释性方法区分 $Λ$CDM 与 Hu-Sawicki $f(R)$ 宇宙学模型,准确率达约 $97\%$,证明 NNs 能最大化巡天探测广义相对论偏差的潜力。

摘要:

我们提出了一种使用神经网络(NNs)来区分宇宙学模型的新方法,并实施了 LIME 作为可解释性方法,以识别影响模型决策的关键特征。我们展示了基于当前星系团簇巡天规范,NNs 从宇宙学大尺度结构数据中提取有意义信息的潜力,针对宇宙学常数与冷暗物质($Λ$CDM)模型及 Hu-Sawicki $f(R)$ 模型。我们发现 NN 能成功区分 $Λ$CDM 与 $f(R)$ 模型,预测正确模型的总体准确率约为 $97\%$,从而证明 NNs 能最大化当前及下一代巡天探测广义相对论偏差的潜力。

英文摘要:

We propose a novel approach using neural networks (NNs) to differentiate between cosmological models, and implemented LIME as an interpretability approach to identify the key features influencing our model's decisions. We show the potential of NNs to enhance the extraction of meaningful information from cosmological large-scale structure data, based on current galaxy-clustering survey specifications, for the cosmological constant and cold dark matter ($Λ$CDM) model and the Hu-Sawicki $f(R)$ model. We find that the NN can successfully distinguish between $Λ$CDM and the $f(R)$ models, by predicting the correct model with approximately $97\%$ overall accuracy, thus demonstrating that NNs can maximize the potential of current and next generation surveys to probe for deviations from general relativity.

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。

↑