发表机构
Indian Institute of Technology, Delhi（印度理工学院德里分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对AI/ML中深度神经架构缺乏可解释性的问题，提出SAMPAT架构，它能学习连续可微函数且近似任意平滑函数，有完全可解释性，实验显示其性能良好，并可用于多种函数表示及优化模型类别选择。
AI 中文摘要
当前人工智能/机器学习的技术现状基于深度神经架构，而这类架构通常缺乏可解释性。可解释性对于分析实验数据以获取见解至关重要，因为定量预测对科学家来说可能并不足够。我们提出了一种三层神经架构SAMPAT（通过多元多项式和解析变换的平滑逼近），它能可证地学习一个连续且处处可微的函数，可任意逼近任何平滑函数。SAMPAT的近似函数可用封闭紧凑的代数、解析表达式表示，具有完全可解释性。在合成和基准数据集上的实验表明，SAMPAT用更简单的表示就能产生有竞争力的性能。通过对神经元之间的连接施加限制，SAMPAT可用于提供一系列近似函数，包括正则和三角多项式、有理表达式、高斯函数、高斯混合函数等。添加跳跃连接后，4到6层的SAMPAT足以表示人工智能/机器学习中广泛使用的大量方法，还能在学习过程中优化模型的类别选择。
英文摘要
The current state of the art in AI/ML rests on deep neural architectures, which, in general, suffer from a lack of interpretability. Interpretability is crucial to gleaning insights while analyzing experimental data, where quantitative predictions may not be adequate for a scientist. We present a three layer neural architecture, SAMPAT (Smooth Approximation via Multivariate Polynomials and Analytic Transformations), that can provably learn a continuous, everywhere differentiable function, that can approximate any smooth function arbitrarily closely. SAMPAT's approximant can be expressed as a closed and compact algebraic, analytic expression, providing complete interpretability. Experiments on synthetic and benchmark datasets indicate that SAMPAT yields competitive performance with simpler representations. For many tasks, a two layer SAMPAT suffices. By imposing restrictions on the connectivity between neurons, SAMPAT may be used to provide a range of approximants, including regular and trigonometric polynomials, rational expressions, Gaussians, mixtures of Gaussians, as well as arbitrary combinations of the same; without restrictions, it learns a suitable structure. SAMPAT may be used to factorize polynomials and model nonlinear systems. With the addition of skip connections, a 4 to 6 layer SAMPAT is adequate to represent a substantive range of methods widely used in AI/ML, allowing the choice of a model's family, not just its parameters, to also be optimized as part of the learning process.
Comments7 pages
