BYR Achieve · 镜像论坛

在上一期AI文献推荐中，我们为您推荐了深度学习的热点文献，包括通过深度学习预测未知原发性癌症的起源，基于贝叶斯深度学习的晶体结构识别方法，基于深度学习的步态识别，以及面向手绘素描数据的深度学习技术及其应用。本期我们为您选取了4篇文献，介绍人工智能应用于其他学科的热点文献。包括基于深度神经网络的古籍恢复，利用人工智能机器学习指导数学直觉，气泡铸造软体机器人，人工智能与量子力学方法在化学中的应用，推送给相关领域的科研人员。文献一基于深度神经网络的古籍恢复 Restoring and attributing ancient texts using deep neural networks Yannis Assael, etc. NATURE, 2022, 603: 280–283 Ancient history relies on disciplines such as epigraphy—the study of inscribed texts known as inscriptions—for evidence of the thought, language, society and history of past civilizations1. However, over the centuries, many inscriptions have been damaged to the point of illegibility, transported far from their original location and their date of writing is steeped in uncertainty. Here we present Ithaca, a deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. Ithaca is designed to assist and expand the historian’s workflow. The architecture of Ithaca focuses on collaboration, decision support and interpretability. While Ithaca alone achieves 62% accuracy when restoring damaged texts, the use of Ithaca by historians improved their accuracy from 25% to 72%, confirming the synergistic effect of this research tool. Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history. This research shows how models such as Ithaca can unlock the cooperative potential between artificial intelligence and historians, transformationally impacting the way that we study and write about one of the most important periods in human history. 阅读原文：https://www.nature.com/articles/s41586-022-04448-z The deep neural network Ithaca’s outputs 文献二利用人工智能机器学习指导数学直觉 Advancing mathematics by guiding human intuition with AI Alex Davies, etc. NATURE, 2021, 600: 70–74 The practice of mathematics involves discovering patterns and using these to formulate and prove conjectures, resulting in theorems. Since the 1960s, mathematicians have used computers to assist in the discovery of patterns and formulation of conjectures1, most famously in the Birch and Swinnerton-Dyer conjecture2, a Millennium Prize Problem3. Here we provide examples of new fundamental results in pure mathematics that have been discovered with the assistance of machine learning—demonstrating a method by which machine learning can aid mathematicians in discovering new conjectures and theorems. We propose a process of using machine learning to discover potential patterns and relations between mathematical objects, understanding them with attribution techniques and using these observations to guide intuition and propose conjectures. We outline this machine-learning-guided framework and demonstrate its successful application to current research questions in distinct areas of pure mathematics, in each case showing how it led to meaningful mathematical contributions on important open problems: a new connection between the algebraic and geometric structure of knots, and a candidate algorithm predicted by the combinatorial invariance conjecture for symmetric groups4. Our work may serve as a model for collaboration between the fields of mathematics and artificial intelligence (AI) that can achieve surprising results by leveraging the respective strengths of mathematicians and machine learning. 阅读原文：https://www.nature.com/articles/s41586-021-04086-x Flowchart of the framework 文献三气泡铸造软体机器人 Bubble casting soft robotics Trevor J. Jones, etc. NATURE, 2021, 599: 229–233 Inspired by living organisms, soft robots are developed from intrinsically compliant materials, enabling continuous motions that mimic animal and vegetal movement1. In soft robots, the canonical hinges and bolts are replaced by elastomers assembled into actuators programmed to change shape following the application of stimuli, for example pneumatic inflation2,3,4,5. The morphing information is typically directly embedded within the shape of these actuators, whose assembly is facilitated by recent advances in rapid prototyping techniques6,7,8,9,10,11. Yet, these manufacturing processes have limitations in scalability, design flexibility and robustness. Here we demonstrate a new all-in-one methodology for the fabrication and the programming of soft machines. Instead of relying on the assembly of individual parts, our approach harnesses interfacial flows in elastomers that progressively cure to robustly produce monolithic pneumatic actuators whose shape can easily be tailored to suit applications ranging from artificial muscles to grippers. We rationalize the fluid mechanics at play in the assembly of our actuators and model their subsequent morphing. We leverage this quantitative knowledge to program these soft machines and produce complex functionalities, for example sequential motion obtained from a monotonic stimulus. We expect that the flexibility, robustness and predictive nature of our methodology will accelerate the proliferation of soft robotics by enabling the assembly of complex actuators, for example long, tortuous or vascular structures, thereby paving the way towards new functionalities stemming from geometric and material nonlinearities. 阅读原文：https://www.nature.com/articles/s41586-021-04029-6 From flow to programmed actuation 文献四人工智能与量子力学方法在化学中的应用 Artificial intelligence-enhanced quantum chemical method with broad applicability Peikun Zheng, etc. NATURE COMMUNICATIONS, 2021, 12: 1–13 High-level quantum mechanical (QM) calculations are indispensable for accurate explanation of natural phenomena on the atomistic level. Their staggering computational cost, however, poses great limitations, which luckily can be lifted to a great extent by exploiting advances in artificial intelligence (AI). Here we introduce the general-purpose, highly transferable artificial intelligence–quantum mechanical method 1 (AIQM1). It approaches the accuracy of the gold-standard coupled cluster QM method with high computational speed of the approximate low-level semiempirical QM methods for the neutral, closed-shell species in the ground state. AIQM1 can provide accurate ground-state energies for diverse organic compounds as well as geometries for even challenging systems such as large conjugated compounds (fullerene C60) close to experiment. This opens an opportunity to investigate chemical compounds with previously unattainable speed and accuracy as we demonstrate by determining geometries of polyyne molecules—the task difficult for both experiment and theory. Noteworthy, our method’s accuracy is also good for ions and excited-state properties, although the neural network part of AIQM1 was never fitted to these properties. 阅读原文：https://www.nature.com/articles/s41467-021-27340-2 The design of the artificial intelligence–quantum mechanical method 1 (AIQM1)

热点文献带您关注AI领域的最新进展——图书馆前沿文献专题推荐