David Carlson
Civil and Environmental Engineering
Associate Professor of Civil and Environmental Engineering
Research Interests
Machine learning, predictive modeling, health data science, statistical neuroscience
Bio
My general research focus is on developing novel machine learning and artificial intelligence techniques that can be used to accelerate scientific discovery. I work extensively both on the fundamental theory and algorithms as well as translating them into scientific applications. I have extensive partnerships deploying machine learning techniques in environmental health, mental health, and neuroscience.
Education
- Ph.D. Duke University, 2015
Positions
- Associate Professor of Civil and Environmental Engineering
- Assistant Professor in Biostatistics & Bioinformatics
- Assistant Professor in the Department of Electrical and Computer Engineering
- Assistant Professor of Computer Science
- Faculty Network Member of the Duke Institute for Brain Sciences
Courses Taught
- ME 555: Advanced Topics in Mechanical Engineering
- EGR 393: Research Projects in Engineering
- ECE 899: Special Readings in Electrical Engineering
- ECE 494: Projects in Electrical and Computer Engineering
- ECE 493: Projects in Electrical and Computer Engineering
- ECE 392: Projects in Electrical and Computer Engineering
- COMPSCI 394: Research Independent Study
- COMPSCI 393: Research Independent Study
- CEE 780: Internship
- CEE 702: Graduate Colloquium
- CEE 690: Advanced Topics in Civil and Environmental Engineering
Publications
- Jain V, Mukherjee A, Banerjee S, Madhwal S, Bergin MH, Bhave P, et al. A hybrid approach for integrating micro-satellite images and sensors network-based ground measurements using deep learning for high-resolution prediction of fine particulate matter (PM
2.5 ) over an indian city, lucknow (Accepted). Atmospheric Environment. 2024 Dec 1;338. - Calhoun ZD, Black MS, Bergin M, Carlson D. Refining Citizen Climate Science: Addressing Preferential Sampling for Improved Estimates of Urban Heat. Environmental Science and Technology Letters. 2024 Aug 13;11(8):845–50.
- Hughes DN, Klein MH, Walder-Christensen KK, Thomas GE, Grossman Y, Waters D, et al. A widespread electrical brain network encodes anxiety in health and depressive states. bioRxiv. 2024 Jun 30;
- Walder-Christensen K, Abdelaal K, Klein H, Thomas GE, Gallagher NM, Talbot A, et al. Electome network factors: Capturing emotional brain networks related to health and disease. Cell Rep Methods. 2024 Jan 22;4(1):100691.
- Calhoun ZD, Willard F, Ge C, Rodriguez C, Bergin M, Carlson D. Estimating the effects of vegetation and increased albedo on the urban heat island effect with spatial causal inference. Scientific reports. 2024 Jan;14(1):540.
- Grossman YS, Talbot A, Gallagher NM, Thomas GE, Fink AJ, Walder-Christensen KK, et al. A widespread oscillatory network encodes an aggressive internal state. Cold Spring Harbor Laboratory. 2022.
- Jiang Z, Zheng T, Bergin M, Carlson D. Improving spatial variation of ground-level PM
2.5 prediction with contrastive learning from satellite imagery. Science of Remote Sensing. 2022 Jun 1;5. - Mague SD, Talbot A, Blount C, Walder-Christensen KK, Duffney LJ, Adamson E, et al. Brain-wide electrical dynamics encode individual appetitive social behavior. Neuron. 2022 May 18;110(10):1728-1741.e7.
- Bey AL, Walder-Christensen KK, Goffinet J, Adamson E, Lanier N, Mague SD, et al. 6.28 Identifying Networks Underlying Sleep Disruption in Autism Spectrum Disorder Mouse Models. In: Journal of the American Academy of Child & Adolescent Psychiatry. Elsevier BV; 2021. p. S167–S167.
- Dunn TW, Marshall JD, Severson KS, Aldarondo DE, Hildebrand DGC, Chettih SN, et al. Geometric deep learning enables 3D kinematic profiling across species and environments. Nat Methods. 2021 May;18(5):564–73.
- Zheng T, Bergin M, Wang G, Carlson D. Local PM
2.5 hotspot detector at 300 m resolution: A random forest-convolutional neural network joint model jointly trained on satellite images and meteorology. Remote Sensing. 2021 Apr 1;13(7). - Carson W, Talbot A, Carlson D. AugmentedPCA: A Python Package of Supervised and Adversarial Linear Factor Models. NeurIPS Workshop on Learning Meaningful Representations of Life. 2021;
- Zhou T, Li Y, Wu Y, Carlson D. Estimating Uncertainty Intervals from Collaborating Networks. Journal of Machine Learning Research. 2021;
- Loring Z, Mehrotra S, Piccini JP, Camm J, Carlson D, Fonarow GC, et al. Machine learning does not improve upon traditional regression in predicting outcomes in atrial fibrillation: an analysis of the ORBIT-AF and GARFIELD-AF registries. In: Europace. 2020. p. 1635–44.
- Isaev DY, Tchapyjnikov D, Cotten CM, Tanaka D, Martinez N, Bertran M, et al. Attention-Based Network for Weak Labels in Neonatal Seizure Detection. Proc Mach Learn Res. 2020 Aug;126:479–507.
- Isaev DY, Major S, Murias M, Carpenter KLH, Carlson D, Sapiro G, et al. Relative Average Look Duration and its Association with Neurophysiological Activity in Young Children with Autism Spectrum Disorder. Sci Rep. 2020 Feb 5;10(1):1912.
- Zheng T, Bergin MH, Hu S, Miller J, Carlson DE. Estimating ground-level PM2. 5 using micro-satellite images by a convolutional neural network and random forest approach. Atmospheric Environment. 2020;117451–117451.
- Isaev DY, Major S, Murias M, Carpenter KLH, Carlson D, Sapiro G, et al. Relative Average Look Duration and its Association with Neurophysiological Activity in Young Children with Autism Spectrum Disorder. Scientific Reports. 2020;10:1–11.
- Cheng P, Li Y, Zhang X, Cheng L, Carlson D, Carin L. Gaussian-Process-Based Dynamic Embedding for Textual Networks. In: AAAI Conference on Artificial Intelligence. 2020.
- Talbot A, Dunson D, Dzirasa K, Carlson D. Supervised Autoencoders Learn Robust Joint Factor Models of Neural Activity. arXiv preprint arXiv:200405209. 2020;
- Lee J, Mitelut C, Shokri H, Kinsella I, Dethe N, Wu S, et al. YASS: Yet Another Spike Sorter applied to large-scale multi-electrode array recordings in primate retina. bioRxiv. 2020;
- Zheng T, Bergin MH, Sutaria R, Tripathi SN, Caldow R, Carlson DE. Gaussian process regression model for dynamically calibrating and surveilling a wireless low-cost particulate matter sensor network in Delhi. Atmospheric Measurement Techniques. 2019 Sep 26;12(9):5161–81.
- Li Y, Gan Z, Shen Y, Liu J, Cheng Y, Wu Y, et al. Storygan: A sequential conditional gan for story visualization. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2019. p. 6322–31.
- Zheng T, Bergin MH, Sutaria R, Tripathi SN, Caldow R, Carlson DE. Supplementary material to "Gaussian Process regression model for dynamically calibrating a wireless low-cost particulate matter sensor network in Delhi". 2019 Mar 1;
- Li Y, Murias M, Major S, Dawson G, Carlson DE. On Target Shift in Adversarial Domain Adaptation. In: International Conference on Artificial Intelligence and Statistics. 2019.
- Norris C, Fang L, Barkjohn KK, Carlson D, Zhang Y, Mo J, et al. Sources of volatile organic compounds in suburban homes in Shanghai, China, and the impact of air filtration on compound concentrations. Chemosphere. 2019;231:256–68.
- Zheng T, Bergin MH, Sutaria R, Tripathi SN, Caldow R, Carlson DE. Gaussian Process regression model for dynamically calibrating a wireless low-cost particulate matter sensor network in Delhi. Atmos Meas Tech Discuss. 2019;1–28.
- Carlson D, Carin L. Continuing progress of spike sorting in the era of big data. Current opinion in neurobiology. 2019;55:90–6.
- Rudin C, Carlson D. The Secrets of Machine Learning: Ten Things You Wish You Had Known Earlier to Be More Effective at Data Analysis. In: Operations Research & Management Science in the Age of Analytics. INFORMS; 2019. p. 44–72.
- Zheng T, Bergin MH, Johnson KK, Tripathi SN, Shirodkar S, Landis MS, et al. Field evaluation of low-cost particulate matter sensors in high-and low-concentration environments. Atmospheric Measurement Techniques. 2018 Aug 22;11(8):4823–46.
- Goldstein BA, Carlson D, Bhavsar NA. Subject Matter Knowledge in the Age of Big Data and Machine Learning. JAMA Netw Open. 2018 Aug 3;1(4):e181568.
- Zheng T, Bergin MH, Johnson KK, Tripathi SN, Shirodkar S, Landis MS, et al. Supplementary material to "Field evaluation of low-cost particulate matter sensors in high and low concentration environments". 2018 Apr 23;
- Hultman R, Ulrich K, Sachs BD, Blount C, Carlson DE, Ndubuizu N, et al. Brain-wide Electrical Spatiotemporal Dynamics Encode Depression Vulnerability. Cell. 2018 Mar 22;173(1):166-180.e14.
- Vu M-AT, Adalı T, Ba D, Buzsáki G, Carlson D, Heller K, et al. A Shared Vision for Machine Learning in Neuroscience. J Neurosci. 2018 Feb 14;38(7):1601–7.
- Liang KJ, Heilmann G, Gregory C, Diallo SO, Carlson D, Spell GP, et al. Automatic threat recognition of prohibited items at aviation checkpoint with x-ray imaging: a deep learning approach. In: Anomaly Detection and Imaging with X-Rays (ADIX) III. 2018. p. 1063203–1063203.
- Zheng T, Bergin MH, Johnson KK, Tripathi SN, Shirodkar S, Landis MS, et al. Field evaluation of low-cost particulate matter sensors in high and low concentration environments. Atmospheric Measurement Techniques. 2018;
- Li Y, Min MR, Shen D, Carlson D, Carin L. Video Generation From Text. In: AAAI Conference on Artificial Intelligence. 2018.
- Li Y, Carlson DE, others. Extracting relationships by multi-domain matching. In: Advances in Neural Information Processing Systems. 2018. p. 6798–809.
- Carlson D, David LK, Gallagher NM, Vu M-AT, Shirley M, Hultman R, et al. Dynamically Timed Stimulation of Corticolimbic Circuitry Activates a Stress-Compensatory Pathway. Biol Psychiatry. 2017 Dec 15;82(12):904–13.
- Li Y, Murias M, Major S, Dawson G, Dzirasa K, Carin L, et al. Targeting EEG/LFP synchrony with neural nets. In: Advances in Neural Information Processing Systems. 2017. p. 4621–31.
- Hultman R, Ulrich K, Sachs B, Blount C, Carlson D, Ndubuizu N, et al. A convergent depression vulnerability pathway encoded by emergent spatiotemporal dynamics. bioRxiv. 2017;154708–154708.
- Pakman A, Gilboa D, Carlson D, Paninski L. Stochastic Bouncy Particle Sampler. In: International Conference on Machine Learning. 2017.
- Gallagher NM, Ulrich K, Talbot A, Dzirasa K, Carin L, Carlson DE. Cross-Spectral Factor Analysis. Advances in Neural Information Processing Systems. 2017;
- Li Y, Murias M, Major S, Dawson G, Dzirasa K, Carin L, et al. Targeting EEG/LFP Synchrony with Neural Nets. Advances in Neural Information Processing Systems. 2017;
- Lee J, Carlson D, Shokri H, Yao W, Goetz G, Hagen E, et al. YASS: Yet Another Spike Sorter. Advances in Neural Information Processing Systems. 2017;
- Gallagher NM, Ulrich K, Talbot A, Dzirasa K, Carin L, Carlson DE. Cross-spectral factor analysis. In: Advances in Neural Information Processing Systems. 2017. p. 6843–53.
- Hultman R, Mague SD, Li Q, Katz BM, Michel N, Lin L, et al. Dysregulation of Prefrontal Cortex-Mediated Slow-Evolving Limbic Dynamics Drives Stress-Induced Emotional Pathology. Neuron. 2016 Jul 20;91(2):439–52.
- Li C, Chen C, Carlson D, Carin L. Preconditioned stochastic gradient Langevin dynamics for deep neural networks. In: AAAI Conference on Artificial Intelligence. 2016.
- Carlson D, Hsieh Y-P, Collins E, Carin L, Cevher V. Stochastic Spectral Descent for Discrete Graphical Models. 2016;
- Song Z, Henao R, Carlson D, Carin L. Learning sigmoid belief networks via Monte Carlo expectation maximization. In: Artificial Intelligence and Statistics. 2016. p. 1347–55.
- Chen C, Carlson D, Gan Z, Li C, Carin L. Bridging the gap between stochastic gradient MCMC and stochastic optimization. In: Artificial Intelligence and Statistics. 2016. p. 1051–60.
- Merel J, Carlson D, Paninski L, Cunningham JP. Neuroprosthetic decoder training as imitation learning. PLoS computational biology. 2016;12.
- Kaganovsky Y, Odinaka I, Carlson D, Carin L. Parallel Majorization Minimization with Dynamically Restricted Domains for Nonconvex Optimization. In: Artificial Intelligence and Statistics. 2016. p. 1497–505.
- Carlson DE, Stinson P, Pakman A, Paninski L. Partition functions from rao-blackwellized tempered sampling. In: 33rd International Conference on Machine Learning, ICML 2016. 2016. p. 4248–62.
- Carlson D, Cevher V, Carin L. Stochastic spectral descent for restricted Boltzmann machines. In: Artificial Intelligence and Statistics. 2015. p. 111–9.
- Carlson DE, Collins E, Hsieh Y-P, Carin L, Cevher V. Preconditioned spectral descent for deep learning. In: Advances in Neural Information Processing Systems. 2015. p. 2971–9.
- Gan Z, Henao R, Carlson D, Carin L. Learning deep sigmoid belief networks with data augmentation. In: Artificial Intelligence and Statistics. 2015. p. 268–76.
- Carlson D. Stochastic Inference and Bayesian Nonparametric Models in Electrophysiological Time Series. 2015.
- Ulrich KR, Carlson DE, Dzirasa K, Carin L. GP kernels for cross-spectrum analysis. In: Advances in neural information processing systems. 2015. p. 1999–2007.
- Gan Z, Li C, Henao R, Carlson DE, Carin L. Deep Temporal Sigmoid Belief Networks for Sequence Modeling. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R, editors. NIPS. 2015. p. 2467–75.
- Gan Z, Li C, Henao R, Carlson DE, Carin L. Deep temporal sigmoid belief networks for sequence modeling. Advances in Neural Information Processing Systems. 2015;2467–75.
- Gan Z, Chen C, Henao R, Carlson D, Carin L. Scalable Deep Poisson Factor Analysis for Topic Modeling. In: ICML. 2015.
- Carlson DE, Borg JS, Dzirasa K, Carin L. On the Relationship Between LFP & Spiking Data. In: Advances in Neural Information Processing Systems. 2014.
- Ulrich K, Carlson DE, Lian W, Borg JS, Dzirasa K, Carin L. Analysis of Brain States from Multi-Region LFP Time-Series. In: Advances in Neural Information Processing Systems. 2014.
- Hu C, Ryu E, Carlson D, Wang Y, Carin L. Latent Gaussian models for topic modeling. In: Artificial Intelligence and Statistics. 2014. p. 393–401.
- Carlson DE, Borg JS, Dzirasa K, Carin L. On the relations of LFPs & Neural Spike Trains. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ, editors. NIPS. 2014. p. 2060–8.
- Wang L, Carlson DE, Rodrigues MRD, Calderbank R, Carin L. A Bregman matrix and the gradient of mutual information for vector Poisson and Gaussian channels. IEEE Transactions on Information Theory. 2014;60:2611–29.
- Carlson DE, Rao V, Vogelstein JT, Carin L. Real-time inference for a gamma process model of neural spiking. Advances in Neural Information Processing Systems. 2013;2805–13.
- Carlson DE, Vogelstein JT, Wu Q, Lian W, Zhou M, Stoetzner CR, et al. Multichannel electrophysiological spike sorting via joint dictionary learning and mixture modeling. IEEE Transactions on Biomedical Engineering. 2013;61:41–54.
- Karumbaiah L, Saxena T, Carlson D, Patil K, Patkar R, Gaupp EA, et al. Relationship between intracortical electrode design and chronic recording function. Biomaterials. 2013;34:8061–74.
- Wang L, Carlson DE, Rodrigues M, Wilcox D, Calderbank R, Carin L. Designed measurements for vector count data. Advances in neural information processing systems. 2013;1142–50.
- Chen M, Carlson D, Zaas A, Woods CW, Ginsburg GS, Hero A, et al. Detection of viruses via statistical gene expression analysis. IEEE Trans Biomed Eng. 2011 Mar;58(3):468–79.
- Chen B, Carlson DE, Carin L. On the analysis of multi-channel neural spike data. In: Advances in Neural Information Processing Systems. 2011. p. 936–44.
- Cheng P, Li Y, Zhang X, Chen L, Carlson D, Carin L. Dynamic Embedding on Textual Networks via a Gaussian Process.
In The News
- For Many Urban Residents, It’s Hotter Than Their Weather App Says (Jun 27, 2024 | Pratt School of Engineering)
- Eyes in the Sky Bring Good News on Trash Burning in the Maldives (Jul 14, 2023 | Pratt School of Engineering)
- Students Find Interdisciplinary Exploration and Connection in Winter Breakaway Courses (Jan 21, 2021 | )
- David Carlson: Engineering and Machine Learning for Better Medicine (Jan 9, 2018 | Duke Research Blog)
- David Carlson: Generating Scientific Understanding from Machine Learning (Aug 24, 2017 | Pratt School of Engineering)