Automated discovery of fundamental variables hidden in experimental data

Chen, Boyuan; Huang, Kuang; Raghupathi, Sunand; Chandratreya, Ishaan; Du, Qiang; Lipson, Hod

doi:10.1038/s43588-022-00281-6

Cited by 70 publications

(58 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, an active area of AI is explainability [101][102][103] . Interestingly, work is now taking place that allows AI to completely describe the phenomenon 104 . At this point, the results show an effective technique to drastically reduce run-time.…”

Section: Methodology and Experimental Resultsmentioning

confidence: 99%

Rapidly predicting Kohn–Sham total energy using data-centric AI

Kurban

Dalkılıç

2022

Sci Rep

View full text Add to dashboard Cite

Predicting material properties by solving the Kohn-Sham (KS) equation, which is the basis of modern computational approaches to electronic structures, has provided significant improvements in materials sciences. Despite its contributions, both DFT and DFTB calculations are limited by the number of electrons and atoms that translate into increasingly longer run-times. In this work we introduce a novel, data-centric machine learning framework that is used to rapidly and accurately predicate the KS total energy of anatase $${\mathrm{TiO}}_2$$ TiO 2 nanoparticles (NPs) at different temperatures using only a small amount of theoretical data. The proposed framework that we call co-modeling eliminates the need for experimental data and is general enough to be used over any NPs to determine electronic structure and, consequently, more efficiently study physical and chemical properties. We include a web service to demonstrate the effectiveness of our approach.

show abstract

Section: Methodology and Experimental Resultsmentioning

confidence: 99%

Rapidly predicting Kohn–Sham total energy using data-centric AI

Kurban

Dalkılıç

2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Our main motivation in this work was to understand regulation in complex biological systems. Often, such systems are “reverse engineered” – for example, using System Identification or other methods, to build mathematical models based on observed data [Ljung, 1998, Schmidt and Lipson, 2009, Chen et al, 2022, Daniels and Nemenman, 2015, Shen et al, 2021, Haber and Schneidman, 2022]. A model can then be investigated to shed light on the functionality of the system, its robustness and other properties.…”

Section: Discussionmentioning

confidence: 99%

Identifying Regulation with Adversarial Surrogates

Teichner

Shomar

Barak

et al. 2022

Preprint

View full text Add to dashboard Cite

Homeostasis, the ability to maintain a relatively constant internal environment in the face of perturbations, is a hallmark of biological systems. It is believed that this constancy is achieved through multiple internal regulation and control processes. Given observations of a system, or even a detailed model of one, it is both valuable and extremely challenging to extract the control objectives of the homeostatic mechanisms. In this work, we develop a robust data-driven method to identify these objectives, namely to understand: what does the system care about?. We propose an algorithm, Identifying Regulation with Adversarial Surrogates (IRAS), that receives an array of temporal measurements of the system, and outputs a candidate for the control objective, expressed as a combination of observed variables. IRAS is an iterative algorithm consisting of two competing players. The first player, realized by an artificial deep neural network, aims to minimize a measure of invariance we refer to as the coefficient of regulation. The second player aims to render the task of the first player more difficult by forcing it to extract information about the temporal structure of the data, which is absent from similar surrogate data. We test the algorithm on two synthetic and one natural data set, demonstrating excellent empirical results. Interestingly, our approach can also be used to extract conserved quantities, e.g., energy and momentum, in purely physical systems, as we demonstrate empirically.

show abstract

“…Current trends in explainable AI include the integration of domain knowledge in the design of AI architectures, training and optimization schemes, while also leaving room for serendipitous discovery 51,52 . At the end of the day we expect AI to shed light on novel features and patterns hidden in experimental datasets that current theories or phenomenology have not been able to predict or elucidate 53 .…”

Section: Agreed-upon Approaches/best Practices To Identify Foundation...mentioning

confidence: 99%

FAIR for AI: An interdisciplinary, international, inclusive, and diverse community building perspective

Huerta¹,

Blaiszik²,

Brinson³

et al. 2022

Preprint

View full text Add to dashboard Cite

A foundational set of findable, accessible, interoperable, and reusable (FAIR) principles were proposed in 2016 as prerequisites for proper data management and stewardship, with the goal of enabling the reusability of scholarly data. The principles were also meant to apply to other digital assets, at a high level, and over time, the FAIR guiding principles have been reinterpreted or extended to include the software, tools, algorithms, and workflows that produce data. FAIR principles are now being adapted in the context of AI models and datasets. Here, we present the perspectives, vision, and experiences of researchers from different countries, disciplines, and backgrounds who are leading the definition and adoption of FAIR principles in their communities of practice, and discuss outcomes that may result from pursuing and incentivizing FAIR AI research. The material for this report builds on the FAIR for AI Workshop held at Argonne National Laboratory on June 7, 2022.

show abstract

Automated discovery of fundamental variables hidden in experimental data

Cited by 70 publications

References 39 publications

Rapidly predicting Kohn–Sham total energy using data-centric AI

Rapidly predicting Kohn–Sham total energy using data-centric AI

Identifying Regulation with Adversarial Surrogates

FAIR for AI: An interdisciplinary, international, inclusive, and diverse community building perspective

Contact Info

Product

Resources

About