Stefano Ermon
Associate Professor of Computer Science and Senior Fellow at the Woods Institute for the Environment
Bio
I am an Assistant Professor in the Department of Computer Science at Stanford University, where I am affiliated with the Artificial Intelligence Laboratory and a fellow of the Woods Institute for the Environment.
My research is centered on techniques for scalable and accurate inference in graphical models, statistical modeling of data, large-scale combinatorial optimization, and robust decision making under uncertainty, and is motivated by a range of applications, in particular ones in the emerging field of computational sustainability.
Academic Appointments
-
Associate Professor, Computer Science
-
Senior Fellow, Stanford Woods Institute for the Environment
-
Faculty Affiliate, Institute for Human-Centered Artificial Intelligence (HAI)
Honors & Awards
-
Sloan Research Fellowship, Alfred P. Sloan Foundation
-
IJCAI Computers and Thought Award, IJCAI
-
Microsoft Research Faculty Fellowship, Microsoft Research
-
NSF CAREER Award, National Science Foundation
-
ONR Young Investigator Award, Office of Naval Research
-
AFOSR Young Investigator Award, Air Force Office of Scientific Research
-
AWS Machine Learning Research Award, Amazon Web Services (AWS)
-
Sony Faculty Innovation Award, Sony
-
Hellman Fellowship, Hellman Foundation
-
AAAI 2017 Outstanding Paper Award, AAAI
-
Bloomberg Data Science Research Grant, Bloomberg
-
10 World Changing Ideas of 2016, Scientific American
-
First Place, World Bank Big Data Innovation Challenge, World Bank
-
Finalist, NVIDIA Global Impact Award, NVIDIA
Professional Education
-
Ph.D., Cornell University, Computer Science (2015)
2024-25 Courses
-
Independent Studies (14)
- Advanced Reading and Research
CS 499 (Aut, Win, Spr) - Advanced Reading and Research
CS 499P (Aut, Win, Spr) - Curricular Practical Training
CS 390A (Aut, Win, Spr) - Curricular Practical Training
CS 390B (Aut, Win, Spr) - Curricular Practical Training
CS 390C (Aut, Win, Spr) - Independent Project
CS 399 (Aut, Win, Spr) - Independent Project
CS 399P (Aut, Win, Spr) - Independent Work
CS 199 (Aut, Win, Spr) - Master's Research
CME 291 (Aut, Win, Spr) - Part-time Curricular Practical Training
CS 390D (Aut, Win, Spr) - Research
PHYSICS 490 (Aut, Win, Spr) - Senior Project
CS 191 (Aut, Win, Spr) - Supervised Undergraduate Research
CS 195 (Aut, Win, Spr) - Writing Intensive Senior Research Project
CS 191W (Aut, Win, Spr)
- Advanced Reading and Research
-
Prior Year Courses
2023-24 Courses
- Data for Sustainable Development
CS 325B, EARTHSYS 162, EARTHSYS 262 (Aut) - Deep Generative Models
CS 236 (Aut) - Probabilistic Graphical Models: Principles and Techniques
CS 228 (Win)
2022-23 Courses
2021-22 Courses
- Data for Sustainable Development
CS 325B, EARTHSYS 162, EARTHSYS 262 (Aut) - Deep Generative Models
CS 236 (Aut) - Probabilistic Graphical Models: Principles and Techniques
CS 228 (Win)
- Data for Sustainable Development
Stanford Advisees
-
Doctoral Dissertation Reader (AC)
Bernard Lange -
Postdoctoral Faculty Sponsor
Syrine Belakaria, Dongjun Kim, Felix Petersen, Zhuo Zheng -
Doctoral Dissertation Advisor (AC)
Silas Alberti, Amil Merchant -
Master's Program Advisor
Shreyas Agarwal, Eric Chen, Julian Chu, Jessica Chudnovsky, Tianyuan Dai, Gui Dávid, Hidy Han, Jinyoung Kim, Simon Kim, Lingjie Kong, Ryne Reger, Rinnara Sangpisit, Manav Shah, Caroline Wang -
Doctoral Dissertation Co-Advisor (AC)
Jeremy Irvin, Haotian Ye -
Doctoral (Program)
Silas Alberti, Meihua Dang, Jiaqi Han, Aaron Lou, Charlie Marx, Chenlin Meng, Michael Poli, Minkai Xu, Linqi Zhou
All Publications
-
Towards general-purpose representation learning of polygonal geometries
GEOINFORMATICA
2022
View details for DOI 10.1007/s10707-022-00481-2
View details for Web of Science ID 000870986700001
-
Density Ratio Estimation via Infinitesimal Classification
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2022
View details for Web of Science ID 000828072702027
-
Bayesian learning for rapid prediction of lithium-ion battery-cycling protocols
JOULE
2021; 5 (12): 3187-3203
View details for DOI 10.1016/j.joule.2021.10.010
View details for Web of Science ID 000732713600012
-
Scalable deep learning to identify brick kilns and aid regulatory capacity.
Proceedings of the National Academy of Sciences of the United States of America
2021; 118 (17)
Abstract
Improving compliance with environmental regulations is critical for promoting clean environments and healthy populations. In South Asia, brick manufacturing is a major source of pollution but is dominated by small-scale, informal producers who are difficult to monitor and regulate-a common challenge in low-income settings. We demonstrate a low-cost, scalable approach for locating brick kilns in high-resolution satellite imagery from Bangladesh. Our approach identifies kilns with 94.2% accuracy and 88.7% precision and extracts the precise GPS coordinates of every brick kiln across Bangladesh. Using these estimates, we show that at least 12% of the population of Bangladesh (>18 million people) live within 1 km of a kiln and that 77% and 9% of kilns are (illegally) within 1 km of schools and health facilities, respectively. Finally, we show how kilns contribute up to 20.4 mug/[Formula: see text] of [Formula: see text] (particulate matter of a diameter less than 2.5 mum) in Dhaka when the wind blows from an unfavorable direction. We document inaccuracies and potential bias with respect to local regulations in the government data. Our approach demonstrates how machine learning and Earth observation can be combined to better understand the extent and implications of regulatory compliance in informal industry.
View details for DOI 10.1073/pnas.2018863118
View details for PubMedID 33888583
-
Using satellite imagery to understand and promote sustainable development.
Science (New York, N.Y.)
2021; 371 (6535)
Abstract
Accurate and comprehensive measurements of a range of sustainable development outcomes are fundamental inputs into both research and policy. We synthesize the growing literature that uses satellite imagery to understand these outcomes, with a focus on approaches that combine imagery with machine learning. We quantify the paucity of ground data on key human-related outcomes and the growing abundance and improving resolution (spatial, temporal, and spectral) of satellite imagery. We then review recent machine learning approaches to model-building in the context of scarce and noisy training data, highlighting how this noise often leads to incorrect assessment of model performance. We quantify recent model performance across multiple sustainable development domains, discuss research and policy applications, explore constraints to future progress, and highlight research directions for the field.
View details for DOI 10.1126/science.abe8628
View details for PubMedID 33737462
-
Multi-agent Imitation Learning with Copulas
SPRINGER INTERNATIONAL PUBLISHING AG. 2021: 139-156
View details for DOI 10.1007/978-3-030-86486-6_9
View details for Web of Science ID 000712017700009
-
Challenges in KDD and ML for Sustainable Development
ASSOC COMPUTING MACHINERY. 2021: 4031-4032
View details for DOI 10.1145/3447548.3470798
View details for Web of Science ID 000749556804011
-
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000768182705086
-
Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000768182704015
-
Temporal Predictive Coding For Model-Based Planning In Latent Space
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000768182704027
-
Predicting Livelihood Indicators from Community-Generated Street-Level Imagery
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2021: 268-276
View details for Web of Science ID 000680423500031
-
Reward Identification in Inverse Reinforcement Learning
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
View details for Web of Science ID 000683104605049
-
Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
MICROTOME PUBLISHING. 2021
View details for Web of Science ID 000659893803025
-
Geography-Aware Self-Supervised Learning
IEEE. 2021: 10161-10170
View details for DOI 10.1109/ICCV48922.2021.01002
View details for Web of Science ID 000798743200016
-
Efficient Poverty Mapping from High Resolution Remote Sensing Images
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2021: 12-20
View details for Web of Science ID 000680423500002
-
Using publicly available satellite imagery and deep learning to understand economic well-being in Africa.
Nature communications
2020; 11 (1): 2583
Abstract
Accurate and comprehensive measurements of economic well-being are fundamental inputs into both research and policy, but such measures are unavailable at a local level in many parts of the world. Here we train deep learning models to predict survey-based estimates of asset wealth across ~ 20,000 African villages from publicly-available multispectral satellite imagery. Models can explain 70% of the variation in ground-measured village wealth in countries where the model was not trained, outperforming previous benchmarks from high-resolution imagery, and comparison with independent wealth measurements from censuses suggests that errors in satellite estimates are comparable to errors in existing ground data. Satellite-based estimates can also explain up to 50% of the variation in district-aggregated changes in wealth over time, with daytime imagery particularly useful in this task. We demonstrate the utility of satellite-based estimates for research and policy, and demonstrate their scalability by creating a wealth map for Africa's most populous country.
View details for DOI 10.1038/s41467-020-16185-w
View details for PubMedID 32444658
-
Meta-Amortized Variational Inference and Learning
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2020: 6404-6412
View details for Web of Science ID 000667722806060
-
Sliced Score Matching: A Scalable Approach to Density and Score Estimation
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2020: 574-584
View details for Web of Science ID 000722423500052
-
Adaptive Hashing for Model Counting
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2020: 271-280
View details for Web of Science ID 000722423500025
-
Fair Generative Modeling via Weak Supervision
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2020
View details for Web of Science ID 000683178501092
-
Domain Adaptive Imitation Learning
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2020
View details for Web of Science ID 000683178505038
-
Flexible Approximate Inference via Stratified Normalizing Flows
JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2020: 1288-1297
View details for Web of Science ID 000723388600130
-
Closed-loop optimization of fast-charging protocols for batteries with machine learning.
Nature
2020; 578 (7795): 397–402
Abstract
Simultaneously optimizing many design parameters in time-consuming experiments causes bottlenecks in a broad range of scientific and engineering disciplines1,2. One such example is process and control optimization for lithium-ion batteries during materials selection, cell manufacturing and operation. A typical objective is to maximize battery lifetime; however, conducting even a single experiment to evaluate lifetime can take months to years3-5. Furthermore, both large parameter spaces and high sampling variability3,6,7 necessitate a large number of experiments. Hence, the key challenge is to reduce both the number and the duration of the experiments required. Here we develop and demonstrate a machine learning methodology to efficiently optimize a parameter space specifying the current and voltage profiles of six-step, ten-minute fast-charging protocols for maximizing battery cycle life, which can alleviate range anxiety for electric-vehicle users8,9. We combine two key elements to reduce the optimization cost: an early-prediction model5, which reduces the time per experiment by predicting the final cycle life using data from the first few cycles, and a Bayesian optimization algorithm10,11, which reduces the number of experiments by balancing exploration and exploitation to efficiently probe the parameter space of charging protocols. Using this methodology, we rapidly identify high-cycle-life charging protocols among 224 candidates in 16 days (compared with over 500 days using exhaustive search without early prediction), and subsequently validate the accuracy and efficiency of our optimization approach. Our closed-loop methodology automatically incorporates feedback from past experiments to inform future decisions and can be generalized to other applications in battery design and, more broadly, other scientific domains that involve time-intensive experiments and multi-dimensional design spaces.
View details for DOI 10.1038/s41586-020-1994-5
View details for PubMedID 32076218
-
Efficient Object Detection in Large Images Using Deep Reinforcement Learning
IEEE COMPUTER SOC. 2020: 1813–22
View details for Web of Science ID 000578444801090
-
Cloud Removal in Satellite Images Using Spatiotemporal Generative Networks
IEEE COMPUTER SOC. 2020: 1785–94
View details for Web of Science ID 000578444801087
-
Permutation Invariant Graph Generation via Score-Based Generative Modeling
ADDISON-WESLEY PUBL CO. 2020: 4474–83
View details for Web of Science ID 000559931302058
-
Gaussianization Flows
ADDISON-WESLEY PUBL CO. 2020: 4336–44
View details for Web of Science ID 000559931302040
-
A Framework for Sample Efficient Interval Estimation with Control Variates
ADDISON-WESLEY PUBL CO. 2020: 4583–91
View details for Web of Science ID 000559931304020
-
AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2020: 4028-4035
View details for Web of Science ID 000667722804013
-
Streamlining variational inference for constraint satisfaction problems
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT
2019; 2019 (12)
View details for DOI 10.1088/1742-5468/ab371f
View details for Web of Science ID 000510503800005
-
Computational Sustainability: Computing for a Better World and a Sustainable Future
COMMUNICATIONS OF THE ACM
2019; 62 (9): 56–65
View details for DOI 10.1145/3339399
View details for Web of Science ID 000483033900019
-
High-Voltage Charging-Induced Strain, Heterogeneity, and Micro-Cracks in Secondary Particles of a Nickel-Rich Layered Cathode Material
ADVANCED FUNCTIONAL MATERIALS
2019; 29 (18)
View details for DOI 10.1002/adfm.201900247
View details for Web of Science ID 000471330500021
-
Using machine learning to discover shape descriptors for predicting emulsion stability in a microfluidic channel
SOFT MATTER
2019; 15 (6): 1361–72
View details for DOI 10.1039/c8sm02054j
View details for Web of Science ID 000459588200020
-
Predicting Economic Development using Geolocated Wikipedia Articles
ASSOC COMPUTING MACHINERY. 2019: 2698–2706
View details for DOI 10.1145/3292500.3330784
View details for Web of Science ID 000485562502077
-
Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning.
Nature communications
2019; 10 (1): 4927
Abstract
Raman optical spectroscopy promises label-free bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving clinically relevant speeds and accuracies remains challenging due to weak Raman signal from bacterial cells and numerous bacterial species and phenotypes. Here we generate an extensive dataset of bacterial Raman spectra and apply deep learning approaches to accurately identify 30 common bacterial pathogens. Even on low signal-to-noise spectra, we achieve average isolate-level accuracies exceeding 82% and antibiotic treatment identification accuracies of 97.0±0.3%. We also show that this approach distinguishes between methicillin-resistant and -susceptible isolates of Staphylococcus aureus (MRSA and MSSA) with 89±0.1% accuracy. We validate our results on clinical isolates from 50 patients. Using just 10 bacterial spectra from each patient isolate, we achieve treatment identification accuracies of 99.7%. Our approach has potential for culture-free pathogen identification and antibiotic susceptibility testing, and could be readily extended for diagnostics on blood, urine, and sputum.
View details for DOI 10.1038/s41467-019-12898-9
View details for PubMedID 31666527
-
Training Variational Autoencoders with Buffered Stochastic Variational Inference
MICROTOME PUBLISHING. 2019
View details for Web of Science ID 000509687902019
-
Learning Controllable Fair Representations
MICROTOME PUBLISHING. 2019
View details for Web of Science ID 000509687902022
-
Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization
MICROTOME PUBLISHING. 2019
View details for Web of Science ID 000509687902058
-
Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
MICROTOME PUBLISHING. 2019
View details for Web of Science ID 000509687902095
-
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866902066
-
MintNet: Building Invertible Neural Networks with Masked Convolutions
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866902061
-
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866903039
-
Approximating the Permanent by Sampling from Adaptive Partitions
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866900045
-
Generative Modeling by Estimating Gradients of the Data Distribution
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866903052
-
Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulation
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019
View details for Web of Science ID 000535866901087
-
InfoVAE: Balancing Learning and Inference in Variational Autoencoders
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2019: 5885–92
View details for Web of Science ID 000486572500051
-
Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery
ASSOC COMPUTING MACHINERY. 2019: 353–59
View details for DOI 10.1145/3306618.3314263
View details for Web of Science ID 000556121100049
-
Tile2Vec: Unsupervised Representation Learning for Spatially Distributed Data
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2019: 3967–74
View details for Web of Science ID 000485292603121
-
Using machine learning to discover shape descriptors for predicting emulsion stability in a microfluidic channel.
Soft matter
2018
Abstract
In soft matter consisting of many deformable objects, object shapes often carry important information about local forces and their interactions with the local environment, and can be tightly coupled to the bulk properties and functions. In a concentrated emulsion, for example, the shapes of individual droplets are directly related to the local stress arising from interactions with neighboring drops, which in turn determine their stability and the resulting rheological properties. Shape descriptors used in prior work on single drops and dilute emulsions, where droplet-droplet interactions are largely negligible and the drop shapes are simple, are insufficient to fully capture the broad range of droplet shapes in a concentrated system. This paper describes the application of a machine learning method, specifically a convolutional autoencoder model, that learns to: (1) discover a low-dimensional code (8-dimensional) to describe droplet shapes within a concentrated emulsion, and (2) predict whether the drop will become unstable and undergo break-up. The input consists of images (N = 500002) of two-dimensional droplet boundaries extracted from movies of a concentrated emulsion flowing through a confined microfluidic channel as a monolayer. The model is able to faithfully reconstruct droplet shapes, as well as to achieve a classification accuracy of 91.7% in the prediction of droplet break-up, compared with 60% using conventional scalar descriptors based on droplet elongation. It is observed that 4 out of the 8 dimensions of the code are interpretable, corresponding to drop skewness, elongation, throat size, and surface curvature, respectively. Furthermore, the results show that drop elongation, throat size, and surface curvature are dominant factors in predicting droplet break-up for the flow conditions tested. The method presented is expected to facilitate follow-on work to identify the relationship between drop shapes and the interactions with other drops, and to identify potentially new modes of break-up mechanisms in a concentrated system. Finally, the method developed here should also apply to other soft materials such as foams, gels, and cells and tissues.
View details for PubMedID 30570628
-
Learning with Weak Supervision from Physics and Data-Driven Constraints
AI MAGAZINE
2018; 39 (1): 27–38
View details for Web of Science ID 000435949900005
-
Bias and Generalization in Deep Generative Models: An Empirical Study
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
View details for Web of Science ID 000461852005038
-
Variational Rejection Sampling
MICROTOME PUBLISHING. 2018
View details for Web of Science ID 000509385300087
-
Best arm identification in multi-armed bandits with delayed feedback
MICROTOME PUBLISHING. 2018
View details for Web of Science ID 000509385300088
-
The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
AUAI PRESS. 2018: 1031–41
View details for Web of Science ID 000493119200101
-
Bayesian optimization and attribute adjustment
AUAI PRESS. 2018: 1042–52
View details for Web of Science ID 000493119200102
-
End-to-End Learning of Motion Representation for Video Understanding
IEEE. 2018: 6016–25
View details for DOI 10.1109/CVPR.2018.00630
View details for Web of Science ID 000457843606018
-
Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
View details for Web of Science ID 000461823305035
-
Amortized Inference Regularization
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
View details for Web of Science ID 000461823304041
-
Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2018: 3069–76
View details for Web of Science ID 000485488903019
-
Boosted Generative Models
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2018: 3077–84
View details for Web of Science ID 000485488903020
-
Approximate Inference via Weighted Rademacher Complexity
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2018: 6376–83
View details for Web of Science ID 000485488906057
-
Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2018: 3474–81
View details for Web of Science ID 000485488903069
-
Constructing Unrestricted Adversarial Examples with Generative Models
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
View details for Web of Science ID 000461852002082
-
Multi-Agent Generative Adversarial Imitation Learning
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
View details for Web of Science ID 000461852002005
-
Streamlining Variational Inference for Constraint Satisfaction Problems
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2018
View details for Web of Science ID 000461852005016
-
Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning
ASSOC COMPUTING MACHINERY. 2018: 616–25
View details for DOI 10.1145/3219819.3219924
View details for Web of Science ID 000455346400065
-
Deep Transfer Learning for Crop Yield Prediction with Remote Sensing Data
ASSOC COMPUTING MACHINERY. 2018
View details for DOI 10.1145/3209811.3212707
View details for Web of Science ID 000455345900050
-
Coupling between oxygen redox and cation migration explains unusual electrochemistry in lithium-rich layered oxides
NATURE COMMUNICATIONS
2017; 8
View details for DOI 10.1038/s41467-017-02041-x
View details for Web of Science ID 000417702300042
-
Coupling between oxygen redox and cation migration explains unusual electrochemistry in lithium-rich layered oxides.
Nature communications
2017; 8 (1): 2091
Abstract
Lithium-rich layered transition metal oxide positive electrodes offer access to anion redox at high potentials, thereby promising high energy densities for lithium-ion batteries. However, anion redox is also associated with several unfavorable electrochemical properties, such as open-circuit voltage hysteresis. Here we reveal that in Li1.17-x Ni0.21Co0.08Mn0.54O2, these properties arise from a strong coupling between anion redox and cation migration. We combine various X-ray spectroscopic, microscopic, and structural probes to show that partially reversible transition metal migration decreases the potential of the bulk oxygen redox couple by > 1 V, leading to a reordering in the anionic and cationic redox potentials during cycling. First principles calculations show that this is due to the drastic change in the local oxygen coordination environments associated with the transition metal migration. We propose that this mechanism is involved in stabilizing the oxygen redox couple, which we observe spectroscopically to persist for 500 charge/discharge cycles.
View details for DOI 10.1038/s41467-017-02041-x
View details for PubMedID 29233965
View details for PubMedCentralID PMC5727078
-
A Survey on Behavior Recognition Using WiFi Channel State Information
IEEE COMMUNICATIONS MAGAZINE
2017; 55 (10): 98-104
View details for DOI 10.1109/MCOM.2017.1700082
View details for Web of Science ID 000413037100016
-
Autotuning Stencil Computations with Structural Ordinal Regression Learning
IEEE. 2017: 287–96
View details for DOI 10.1109/IPDPS.2017.102
View details for Web of Science ID 000427044800030
-
Label-Free Supervision of Neural Networks with Physics and Domain Knowledge
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2017: 2576-2582
View details for Web of Science ID 000485630702088
-
Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2017: 4559-4565
View details for Web of Science ID 000485630704085
-
General Bounds on Satisfiability Thresholds for Random CSPs via Fourier Analysis
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2017: 3958-3965
View details for Web of Science ID 000485630704002
-
Estimating Uncertainty Online Against an Adversary
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2017: 2110-2116
View details for Web of Science ID 000485630702022
-
Deep Hybrid Models: Bridging Discriminative and Generative Approaches
AUAI PRESS. 2017
View details for Web of Science ID 000493309500085
-
Fast Amortized Inference and Learning in Log-linear Models with Randomly Perturbed Nearest Neighbor Search
AUAI PRESS. 2017
View details for Web of Science ID 000493309500021
-
A-NICE-MC: Adversarial Training for MCMC
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2017
View details for Web of Science ID 000452649405022
-
InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2017
View details for Web of Science ID 000452649403085
-
Monitoring Ethiopian Wheat Fungus with Satellite Imagery and Deep Feature Learning
IEEE. 2017: 1524–32
View details for DOI 10.1109/CVPRW.2017.196
View details for Web of Science ID 000426448300189
-
Unsupervised Data Mining in nanoscale X-ray Spectro-Microscopic Study of NdFeB Magnet
SCIENTIFIC REPORTS
2016; 6
Abstract
Novel developments in X-ray based spectro-microscopic characterization techniques have increased the rate of acquisition of spatially resolved spectroscopic data by several orders of magnitude over what was possible a few years ago. This accelerated data acquisition, with high spatial resolution at nanoscale and sensitivity to subtle differences in chemistry and atomic structure, provides a unique opportunity to investigate hierarchically complex and structurally heterogeneous systems found in functional devices and materials systems. However, handling and analyzing the large volume data generated poses significant challenges. Here we apply an unsupervised data-mining algorithm known as DBSCAN to study a rare-earth element based permanent magnet material, Nd2Fe14B. We are able to reduce a large spectro-microscopic dataset of over 300,000 spectra to 3, preserving much of the underlying information. Scientists can easily and quickly analyze in detail three characteristic spectra. Our approach can rapidly provide a concise representation of a large and complex dataset to materials scientists and chemists. For example, it shows that the surface of common Nd2Fe14B magnet is chemically and structurally very different from the bulk, suggesting a possible surface alteration effect possibly due to the corrosion, which could affect the material's overall properties.
View details for DOI 10.1038/srep34406
View details for Web of Science ID 000384188300001
View details for PubMedID 27680388
View details for PubMedCentralID PMC5041149
-
Combining satellite imagery and machine learning to predict poverty.
Science
2016; 353 (6301): 790-794
Abstract
Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries--Nigeria, Tanzania, Uganda, Malawi, and Rwanda--we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.
View details for DOI 10.1126/science.aaf7894
View details for PubMedID 27540167
-
Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2016: 3929–35
View details for Web of Science ID 000485474203133
-
Generative Adversarial Imitation Learning
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2016
View details for Web of Science ID 000458973703027
-
Probabilistic Inference by Hashing and Optimization
PERTURBATIONS, OPTIMIZATION, AND STATISTICS
2016: 265-288
View details for Web of Science ID 000521530900010
-
Tight Variational Bounds via Random Projections and I-Projections
MICROTOME PUBLISHING. 2016: 1087-1095
View details for Web of Science ID 000508662100118
-
Closing the Gap Between Short and Long XORs for Model Counting
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2016: 3322-3328
View details for Web of Science ID 000485474203050
-
Exact Sampling with Integer Linear Programs and Random Perturbations
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2016: 3248-3254
View details for Web of Science ID 000485474203040
-
Adaptive Concentration Inequalities for Sequential Decision Problems
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2016
View details for Web of Science ID 000458973704018
-
Solving Marginal MAP Problems with NP Oracles and Parity Constraints
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2016
View details for Web of Science ID 000458973703098
-
Variational Bayes on Monte Carlo Steroids
NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2016
View details for Web of Science ID 000458973702006
-
Learning Large-Scale Dynamic Discrete Choice Models of Spatio-Temporal Preferences with Application to Migratory Pastoralism in East Africa
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2015: 644-650
View details for Web of Science ID 000485625500089
-
Uncovering Hidden Structure through Parallel Problem Decomposition for the Set Basis Problem: Application to Materials Discovery
IJCAI-INT JOINT CONF ARTIF INTELL. 2015: 146-154
View details for Web of Science ID 000442637800021
-
Importance Sampling over Sets: A New Probabilistic Inference Scheme
AUAI PRESS. 2015: 355-364
View details for Web of Science ID 000493121100037
-
Pattern Decomposition with Complex Combinatorial Constraints: Application to Materials Discovery
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2015: 636-643
View details for Web of Science ID 000485625500088