拓樸學遇上機器學習
作者 里克（Bastian Rieck）
作者簡介
里克是德國弗里堡大學（University of Fribourg）的機器學習教授，並擔任AI資料科學實驗室（AI for Data-Oriented Science）首席研究員。他研究如何透過幾何學和拓樸學的視角，改善機器學習和 AI所需要的堅實基礎。
譯者 王夏聲
譯者簡介
王夏聲是陽明交通大學應用數學系副教授。
本文出處
本文譯自Bastian Rieck,“Topology Meets Machine Learning: An Introduction Using the Euler Characteristic Transforms”, Notices of the AMS 72（2025）No. 7, AMS。© American Mathematical Society 2008. All rights reserved。感謝AMS與作者同意轉載翻譯。
延伸閱讀
本刊曾刊登的第10期「人工智慧與AlphaGo」與第17期「機器學習」的專題、第18期林軒田的〈什麼是機器學習——機器學習漫談〉以及第19期鄂維南的〈機器學習——數學理論與科學應用〉諸篇文章，讀者可以參照本文閱讀。
參考文獻
[CAD+21] Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, and Debdeep Mukhopadhyay, A survey on adversarial attacks and defences, CAAI Transactions on Intelligence Technology 6 (2021), no. 1, 25–45.
[CMT22] Justin Curry, Sayan Mukherjee, and Katharine Turner, How many directions determine a shape and other sufficiency results for two topological transforms, Trans. Amer. Math. Soc. Ser. B 9 (2022), 1006–1043.
[Ghr25] Robert Ghrist, AI & mathematics as a career (January 2025).
[GLM18] Robert Ghrist, Rachel Levanger, and Huy Mai, Persistent homology and Euler integral transforms, J. Appl. Comput. Topol. 2 (2018), no. 1-2, 55–60.
[HH19] Catherine F. Higham and Desmond J. Higham, Deep learning: an introduction for applied mathematicians, SIAM Rev. 61 (2019), no. 4, 860–891.
[HIZ20] Mustafa Hajij, Kyle Istvan, and Ghada Zamzmi, Cell complex neural networks, “Topological Data Analysis and Beyond” Workshop at NeurIPS, 2020.
[HSW89] Kurt Hornik, Maxwell Stinchcombe, and Halbert White, Multilayer feedforward networks are universal approximators, Neural Networks 2 (1989), no. 5, 359–366.
[MHR24] Kelly Maggs, Celia Hacker, and Bastian Rieck, Simplicial representation learning with neural 𝑘-forms, International Conference on Learning Representations, 2024.
[Mun25] Elizabeth Munch, An invitation to the Euler characteristic transform, Amer. Math. Monthly 132 (2025), no. 1, 15–25.
[PBB+24] Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, and Ghada Zamzmi, Position: Topological deep learning is the new frontier for relational learning, Proceedings of the 41st International Conference on Machine Learning, 2024, pp. 39529–39555.
[RR24] Ernst Röell and Bastian Rieck, Differentiable Euler characteristic transforms for shape classification, International Conference on Learning Representations, 2024.
[Sch22] Jürgen Schmidhuber, Annotated history of modern AI and deep learning, 2022.
[TMB14] Katharine Turner, Sayan Mukherjee, and Doug M. Boyer, Persistent homology transform for modeling shapes and surfaces, Inf. Inference 3 (2014), no. 4, 310–344.
[Vel23] Petar Veličković, Everything is connected: Graph neural networks, Current Opinion in Structural Biology 79 (2023), 102538.
[WAM+22] Dominik J. E. Waibel, Scott Atwell, Matthias Meier, Carsten Marr, and Bastian Rieck, Capturing shape information with multi-scale topological loss terms for 3D reconstruction, Medical Image Computing and Computer Assisted Intervention, 2022, pp. 150–159.
[Won24] Matteo Wong, We’re entering uncharted territory for math, The Atlantic (October 2024).
