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 2012.06006cs.AIcs.LG
收藏

xRAI:通过AI可解释的表示

xRAI: Explainable Representations through AI

Clausthal University of Technology(克劳斯塔尔工业大学);University of Mannheim(曼海姆大学)

Christiann Bartelt, Sascha Marton, Heiner Stuckenschmidt

摘要:

我们提出了xRAI的方法提取符号表示的数学函数的神经网络应该从训练的网络学习。该方法基于训练一个所谓的解释网络的想法,该网络接收训练网络的权重和偏差作为输入,并输出网络应该学习的函数的数值表示,该函数可以直接转换为符号表示。我们表明,解释网络的不同类别的功能,可以训练合成数据离线使用布尔函数和低阶多项式为例。我们表明,培训是相当有效的,结果的质量是有希望的。我们的工作旨在通过使目标函数显式化来为更好地理解神经决策问题做出贡献

英文摘要:

We present xRAI an approach for extracting symbolic representations of the mathematical function a neural network was supposed to learn from the trained network. The approach is based on the idea of training a so-called interpretation network that receives the weights and biases of the trained network as input and outputs the numerical representation of the function the network was supposed to learn that can be directly translated into a symbolic representation. We show that interpretation nets for different classes of functions can be trained on synthetic data offline using Boolean functions and low-order polynomials as examples. We show that the training is rather efficient and the quality of the results are promising. Our work aims to provide a contribution to the problem of better understanding neural decision making by making the target function explicit

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。

↑