Artificial Intelligence and Advanced Materials
Искусственный интеллект и передовые материалы
2022-12-23
SCID: 54.1/u26bgxkc
Discuss with AI
advanced materialsartificial intelligencemachine learningmaterials discoverymaterials science
Figures from the paper
Abstract (AI)
Artificial intelligence (AI) is gaining strength, and materials science can both contribute to and profit from it. In a simultaneous progress race, new materials, systems, and processes can be devised and optimized thanks to machine learning (ML) techniques, and such progress can be turned into innovative computing platforms. Future materials scientists will profit from understanding how ML can boost the conception of advanced materials. This review covers aspects of computation from the fundamentals to directions taken and repercussions produced by computation to account for the origins, procedures, and applications of AI. ML and its methods are reviewed to provide basic knowledge of its implementation and its potential. The materials and systems used to implement AI with electric charges are finding serious competition from other information-carrying and processing agents. The impact these techniques have on the inception of new advanced materials is so deep that a new paradigm is developing where implicit knowledge is being mined to conceive materials and systems for functions instead of finding applications to found materials. How far this trend can be carried is hard to fathom, as exemplified by the power to discover unheard of materials or physical laws buried in data.
Key Findings
1
Data-driven methods may uncover previously unknown materials and physical laws embedded in large datasets.
2
Machine learning is driving a paradigm shift toward designing materials and systems for desired functions rather than identifying applications for existing materials.
3
Machine-learning techniques enable the design and optimization of new materials, systems, and processes, while advanced materials can enable innovative computing platforms.
4
Materials and systems based on electric charges face increasing competition from alternative information-carrying and processing agents.
5
The review connects AI computation fundamentals, development directions, and impacts with materials-science applications and future research opportunities.
Research Object
AI-driven advanced materials, systems, and processes
Research Subject
The use of machine learning to conceive, optimize, and discover advanced materials, systems, and physical laws
Publication Details
Publication Date
2022-12-23
Journal
Advanced Materials
Publisher
ISSN
0935-9648
Cited by
118
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai20
Genetic algorithms in search, optimization, and machine learning1989
Artificial intelligence: a modern approach1995
Reducing the Dimensionality of Data with Neural Networks2006
Neural networks and physical systems with emergent collective computational abilities.1982
Representation Learning: A Review and New Perspectives2013
A survey of transfer learning2016
Artificial neural networks: a tutorial1996
Topological photonics2019
Recent advances and applications of machine learning in solid-state materials science2019
On representing chemical environments2013
Quantum chemistry structures and properties of 134 kilo molecules2014
Machine learning in materials informatics: recent applications and prospects2017
Machine learning & artificial intelligence in the quantum domain: a review of recent progress2018
Explainable Machine Learning for Scientific Insights and Discoveries2020
Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials2018
Experimental demonstration of reservoir computing on a silicon photonics chip2014
Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design2019
Photonic matrix multiplication lights up photonic accelerator and beyond2022
Artificial General Intelligence: Concept, State of the Art, and Future Prospects2014
Classification of crystal structure using a convolutional neural network2017