Professor Yisong Yue gives a tutorial on bandit algorithms.

AI4science

Across science—from astrophysics to molecular biology to economics—researchers are overwhelmed by the sheer amount of data they are collecting. But, this problem is better viewed as an opportunity since, with the right computing resources and algorithmic tools, scientists might unlock new insights from the swathes of data to carry their field forward.

AI4science (or artificial intelligence for science) is an initiative at Caltech led by Anima Anandkumar and Yisong Yue that aims to bring together AI researchers with experts from other disciplines to push modern AI tools into every area of science and engineering. Launched in the summer of 2018, the initiative organizes talks, courses, and tutorials aimed at training researchers from across the scientific spectrum in the theory and practice of machine learning algorithms. Weekly AI4science office hours also allow researchers to ask computer scientists for help—hopefully stimulating new interdisciplinary research at Caltech. Additionally, seed grants for researchers applying AI to new applications in the sciences are allocated yearly through the Carver Mead New Adventures program

Here are a few examples of Caltech professors transferring artificial intelligence and machine learning research to other disciplines.

To find out more about this new initiative, visit the AI4science website.

AI4neuro

Joel Burdick, Richard L. and Dorothy M. Hayman Professor of Mechanical Engineering and Bioengineering, is applying machine learning algorithms (some designed by Caltech’s Professor Yisong Yue) to help patients with spinal cord injuries to walk again. The so-called “neural prosthesis” is a device which plugs into a human’s nerve endings, reads the electrical signals and uses them to control a mobility-assisting device.

AI4climate

Andrew Stuart, Bren Professor of Computing and Mathematical Sciences, is applying machine learning algorithms to build more fine-grained climate models. Working with Professor Tapio Schneider in Caltech’s Climate Dynamics Group, Stuart hopes to build better predictive models of the Earth’s changing climate.

AI4physics

Maria Spiropulu, Professor of Physics, is applying machine learning methods to try to make sense of the floods of data coming in from the Large Hadron Collider at CERN. Currently most of the roughly one petabyte of data collected every second at CERN must be thrown away, so even deciding which data to keep is an important problem in the hunt for signals in the dark.

Awards

The flagship programs of the AI4Science initiative are the selection of AI4Science Graduate and Postdoctoral Fellows and the Cloud Credit Grant program, both of which are sponsored by Amazon AWS. The recipients of this are listed below. Additionally, the AI4Science initiative sponsors awards through the Carver Mead New Adventures Fund and organizes workshops, seminars, summer schools, and other events centered around AI and its applications.

AI4Science/Amazon AWS Fellows

Year	Award Recipient	Advisor
2022-2023	Zhoufan (Francesca) Li	Frances H. Arnold / Yisong Yue
2022-2023	Changhao Xu	Wei Gao
2022-2023	Maria Carilli	Lior S. Pachter
2022-2023	Christopher T. Yeh	Yisong Yue
2022-2023	Yiheng Lin	Adam Wierman /Yisong Yue
2022-2023	Nicholas H. Nelsen	Andrew Stuart
2022-2023	Zihui (Ray) Wu	Katie Bouman
2022-2023	Jing Yu	John Doyle / Adam Wierman
2022-2023	Elena-Sorina Lupu	Soon-Jo Chung
2021-2022	Ignacio Lopez-Gomez	Tapio Schneider
2021-2022	Rebecca Gallivan	Julia R. Greer
2021-2022	Andrew Charbonneau	Chiara Daraio
2021-2022	Zongyi Li	Anima Anandkumar
2021-2022	Bijan Mazaheri	Shuki Bruck / Leonard Schulman
2021-2022	Dmitry Burov	Andrew Stuart
2021-2022	Jennifer J. Sun	Pietro Perona / Yisong Yue
2021-2022	Frankcesco (Frank) Lanfranchi	Doris Tsao (Berkely) / Mikhail Shapiro
2020-2021	Carmen Amo Alonso	John Doyle
2020-2021	Sara Beery	Pietro Perona
2020-2021	Charles Guan	Richard A. Andersen
2020-2021	Kadina Johnston	Frances H. Arnold
2020-2021	Nikola Kovachki	Andrew Stuart
2020-2021	Zhuoran Qiao	Thomas F. Miller III
2020-2021	Guannan Qu	Steven Low / Adam Wierman
2020-2021	He Sun	Katie Bouman

AI4Science/Amazon AWS Cloud Credit Recipients

Year	Project Title	Award Recipients	Division
2022-2023	Developing a DFT-based Ligand-Substrate Prediction Pipeline for Nickel-Catalyzed Reactions.	Sarah Reisman	Chemistry and Chemical Engineering
2022-2023	Exploring the effects of rapidly acting antidepressants on neuronal activity through microscopy and deep learning	David A. Prober, Andrey Andreev, Zack Blumenfeld & Henry A. Lester	Biology and Biological Engineering
2022-2023	Growing Arbitrary Patterns with Neural Reaction-Diffusion	Eric Winfree & Salvador Buse	CS, CNS & BioEng / Engineering and Applied Science
2022-2023	Graph neural networks for volumetric meta-optics design	Andrei Faraon	Applied Physics and EE/Engineering and Applied Science
2022-2023	Physics-based Modeling of Near-Source Tsunami Hazards for Coastal Communities	Ares J. Rosakis & Mohamed Abdelmeguid	Aeronautics & MechE/Engineering and Applied Science
2022-2023	AstroQML: Quantum Machine Learning for Astronomy	Matthew J. Graham	Astronomy
2022-2023	Characterizing and leveraging the expressivity of protein dimerization networks	Michael Elowitz	Biology and Biological Engineering
2022-2023	Finding Rare Astrophysical Sources	Matthew Graham, Lynne Hillenbrand, Michael Coughlin, Andrew Drake & Ashish Mahabal	Astronomy
2022-2023	Activity-Enhanced Self-Assembly of Colloidal Diamonds	John F. Brady	Chemistry and Chemical Engineering
2022-2023	Tracking natural insect populations with AI	Michael H. Dickenson & Joseph Parker	Biology and Biological Engineering
2022-2023	Sentence-level classification of Biological Data for Semi-automated Knowledgebase Curation at WormBase	Paul W. Sternberg	Biology and Biological Engineering
2022-2023	NUPACK: Molecular Programming in the Cloud	Niles A. Pierce	Biology and Biological Engineering
2021-2022	Multiphysical Single Protein Identification - Deep Learning for Multiphysical Single Protein Identification	Michael Roukes Group	Physics, Mathematics and Astronomy
2021-2022	Political Polarization, Geographic Sorting, and Novel Methods for Large Administrative Data	Claudia Kann & Daniel Ebanks	Humanities and Social Sciences
2021-2022	Dynamic Topic Modeling with Spectral Methods	Zhuofang Li	Social Science
2021-2022	Optimized Terapixel Scale Processing of Astronomical Images	Graham (Bruce) Berriman	IPAC
2021-2022	BBE Education	Justin Bois	Biology and Biological Engineering
2021-2022	Using Cloud Computing For The Detection And Prevention of Social Media Misinformation and Harassment	R. Michael Alvarez	Humanities and Social Sciences
2021-2022	Learning an Index of Economic Complexity	Frederick Eberhardt & Patrick Burauel	Humanities and Social Sciences
2021-2022	Harm Reduction in Tobacco Addiction: Pharmacokinetics of Nicotine for Smoking Cessation	Henry A. Lester	Biology and Biological Engineering
2021-2022	NUPACK: Molecular Programming in the Cloud	Niles A. Pierce	Biology and Biological Engineering
2021-2022	Preventing T cell exhaustion by engineering oscillatory circuits	Shirin Shivaei	Bioengineering
2021-2022	The ZTF AGN Catalog	Matthew J. Graham	Astronomy
2021-2022	Computational design of computational protein networks	Michael Elowitz	Biology and Biological Engineering
2020-2021	Text Similarity Query System to Improve Biological Curation of Scientific Articles at WormBase	Paul Sternberg/Hans-Michael Muller/Valerio Arnaboldi/Daniela Raciti/Kimberly Van Auken	Biology and Biological Engineering
2020-2021	Active Drug Delivery	John F. Brady/(Edmond) Tingtao Zhou/Zhiwei Peng	Chemistry and Chemical Engineering
2020-2021	Expanding the Definition of a Functional Protein with Ancestral Sequence Reconstruction for Semi-Supervised Transfer Learning in Protein Engineering	Bruce J. Wittmann/Kadina E. Johnston/Frances H. Arnold	Chemistry and Chemical Engineering
2020-2021	Discovery of Microscopic Control Strategies Involving Active Matter by Using State-of-the-Art Reinforcement Learning Techniques	Dominik Schildknecht/Enrique Amaya/Matt Thomson	Biology and Biological Engineering
2020-2021	Causal Discovery Methods for Astrophysical Data	Frederick Eberhardt/Eric Huff	Humanities and Social Sciences
2020-2021	Computational Lineage Motif Analysis of cell fate decision programs during differentiation	Michael Elowitz	Biology and Biological Engineering
2020-2021	Memory maps as long-term memory storage in recurrent neural networks	James Gornet/ Matt Thomson	Biology and Biological Engineering
2020-2021	Embedding of single cell drug perturbation experiments by graph neural networks	Jialong Jiang/Sisi Chen/Tahmineh Khazaei/Matt Thomson	Biology and Biological Engineering
2020-2021	Millisecond Astronomy with the Zwicky Transient Facility	Mansi Kasliwal/Igor Andreoni/Matthew Graham/Ashish Mahabal/Roger Smith/Stephen Kaye/Sterl Phinney/Richard Walters	Physics, Mathematics and Astronomy
2020-2021	Finding Rare Astrophysical Sources	Mahabal Ashish/Kevin Burdge/Michael Coughlin/Andrew Drake/Dmitry Duev/Matthew Graham/Lynne Hillenbrand/Przemek Mroz/Joannes Van Roestel	Physics, Mathematics and Astronomy
2020-2021	NUPACK: Molecular Programming in the Cloud	Niles Pierce	Biology and Biological Engineering
2020-2021	Development of a high throughput analysis pipeline for whole-brain light sheet imaging during behavior	Andrey Andreev/Amina Kinkhabwala/David Prober	Biology and Biological Engineering

Get involved

Sign up for machinelearning@caltech.edu to receive notifications about AI4science office hours, tutorials, seminars, and workshops.
Apply for a seed grant through the Carver Mead New Adventures program

For more information, reach out to Anima Anandkumar and Yisong Yue.

Giving to AI4science

Thanks to the generous donations of the IST Council members the AI4science initiative kicked off in Fall 2018. The ultimate goal is to able to establish a thriving interdisciplinary community of researchers applying AI to transform the sciences. A gift to the AI4science initiative is an investment in ideas that have the potential to revolutionize the sciences and push the boundaries of AI.