# Browsing by Author "Carlson, David"

###### Results Per Page

###### Sort Options

Item Open Access Applications of Deep Representation Learning to Natural Language Processing and Satellite Imagery(2020) Wang, GuoyinDeep representation learning has shown its effectiveness in many tasks such as text classification and image processing. Many researches have been done to directly improve the representation quality. However, how to improve the representation quality by cooperating ancillary data source or by interacting with other representations is still not fully explored. Also, using representation learning to help other tasks is worth further exploration.

In this work, we explore these directions by solving various problems in natural language processing and image processing. In the natural language processing part, we first discuss how to introduce alternative representations to improve the original representation quality and hence boost the model performance. We then discuss a text representation matching algorithm. By introducing such matching algorithm, we can better align different text representations in text generation models and hence improve the generation qualities.

For the image processing part, we consider a real-world air condition prediction problem: ground-level $PM_{2.5}$ estimation. To solve this problem, we introduce a joint model to improve image representation learning by incorporating image encoder with ancillary data source and random forest model. We the further extend this model with ranking information for semi-supervised learning setup. The semi-supervised model can then utilize low-cost sensors for $PM_{2.5}$ estimation.

Finally, we introduce a recurrent kernel machine concept to explain the representation interaction mechanism within time-dependent neural network models and hence unified a variety of algorithms into a generalized framework.

Item Open Access AugmentedPCA: A Python Package of Supervised and Adversarial Linear Factor Models(NeurIPS Workshop on Learning Meaningful Representations of Life, 2021) Carson, William; Talbot, Austin; Carlson, DavidItem Open Access Estimating the effects of vegetation and increased albedo on the urban heat island effect with spatial causal inference.(Scientific reports, 2024-01) Calhoun, Zachary D; Willard, Frank; Ge, Chenhao; Rodriguez, Claudia; Bergin, Mike; Carlson, DavidThe urban heat island effect causes increased heat stress in urban areas. Cool roofs and urban greening have been promoted as mitigation strategies to reduce this effect. However, evaluating their efficacy remains a challenge, as potential temperature reductions depend on local characteristics. Existing methods to characterize their efficacy, such as computational fluid dynamics and urban canopy models, are computationally burdensome and require a high degree of expertise to employ. We propose a data-driven approach to overcome these hurdles, inspired by recent innovations in spatial causal inference. This approach allows for estimates of hypothetical interventions to reduce the urban heat island effect. We demonstrate this approach by modeling evening temperature in Durham, North Carolina, using readily retrieved air temperature, land cover, and satellite data. Hypothetical interventions such as lining streets with trees, cool roofs, and changing parking lots to green space are estimated to decrease evening temperatures by a maximum of 0.7-0.9 [Formula: see text], with reduced effects on temperature as a function of distance from the intervention. Because of the ease of data access, this approach may be applied to other cities in the U.S. to help them come up with city-specific solutions for reducing urban heat stress.Item Open Access Machine Learning for Uncertainty with Application to Causal Inference(2022) Zhou, TianhuiEffective decision making requires understanding the uncertainty inherent in a problem. This covers a wide scope in statistics, from deriving an estimator to training a predictive model. In this thesis, I will spend three chapters discussing new uncertainty methods developed for solving individual and population level inference problems with their theory and applications in causal inference. I will also detail the limitations of existing approaches and why my proposed methods lead to better performance.

In the first chapter, I will introduce a novel approach, Collaborating Networks (CN), to capture predictive distributions in regression. It defines two neural networks with two distinct loss functions to approximate the cumulative distribution function and its inverse respectively and collectively. This gives CN extra flexibility through bypassing the necessity of assuming an explicit distribution family like Gaussian. Empirically, CN generates sharp intervals with reliable coverage.

In the second chapter, I extend CN to estimate the individual treatment effect in observational studies. It is augmented by a new adjustment scheme developed through representation learning, which is shown to effectively alleviate the imbalance between treatment groups. Moreover, a new evaluation criterion is suggested by combing the estimated uncertainty and variation in utility functions (e.g., variability in risk tolerance) for more comprehensive decision making, while traditional approaches only study an individual’s outcome change due to a potential treatment.

In the last chapter, I will present an analysis pipeline for causal inference with propensity score weighting. Comparing to other pipelines for similar purposes, this package comprises a wider range of functionalities to provide an exhaustive design and analysis platform that enables users to construct different estimators and assess their uncertainties. Itoffers six major advantages: it incorporates (i) visualization and diagnostic tools of checking covariate overlap and balance, (ii) a general class of balancing weights, (iii) comparison for multiple treatments, (iv) simple and augmented (doubly-robust) weighting estimators, (iv) nuisance-adjusted sandwich variances, and (v) ratio estimands for binary and count outcomes.

Item Open Access Neuroprosthetic Decoder Training as Imitation Learning.(PLoS Comput Biol, 2018-02-02) Merel, Josh; Carlson, David; Paninski, Liam; Cunningham, John PNeuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user's intention is not directly observable, recent methods have demonstrated value in training the decoder against a surrogate for the user's intended movement. Here we show that training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available. Specifically, we describe how a generic imitation learning meta-algorithm, dataset aggregation (DAgger), can be adapted to train a generic brain-computer interface. By deriving existing learning algorithms for brain-computer interfaces in this framework, we provide a novel analysis of regret (an important metric of learning efficacy) for brain-computer interfaces. This analysis allows us to characterize the space of algorithmic variants and bounds on their regret rates. Existing approaches for decoder learning have been performed in the cursor control setting, but the available design principles for these decoders are such that it has been impossible to scale them to naturalistic settings. Leveraging our findings, we then offer an algorithm that combines imitation learning with optimal control, which should allow for training of arbitrary effectors for which optimal control can generate goal-oriented control. We demonstrate this novel and general BCI algorithm with simulated neuroprosthetic control of a 26 degree-of-freedom model of an arm, a sophisticated and realistic end effector.Item Open Access Stochastic Inference and Bayesian Nonparametric Models in Electrophysiological Time Series(2015) Carlson, DavidThis thesis presents novel methods for processing electrophysiological time-series from simultaneously recorded electrodes in a brain, as well as providing new inference techniques that are more generally applicable. On spike sorting, I introduce Bayesian nonparametric methods to process multiple electrodes simultaneously, which improves performance when the electrode spacing is less than 100 microns. Furthermore, by treating the spike sorting problem as a single deconvolutional model instead of the conventional 2-step procedure with detection and clustering steps, the over- lapping spike problem is ameliorated. I then show that these detected neurons and their spike trains have dynamic relationships with local field potentials in distinct brain regions, and that the number of distinct relationships appears to cluster.

While these models approach an important scientific problem, it is necessary to have efficient inference in computationally-intensive models. To this end, I intro- duce novel methods for Variational Bayesian inference, as well as introducing a new stochastic inference algorithm called "Stochastic Spectral Descent," which mimics Stochastic Gradient Descent but operates in the Shatten-infinity norm. I show that several common machine learning problems naturally operate in the Shatten-infinity norm, and that this descent method mimics the natural geometry and greatly improves learning efficiency.

Item Open Access Supervised Autoencoders Learn Robust Joint Factor Models of Neural Activity.(CoRR, 2020) Talbot, Austin; Dunson, David; Dzirasa, Kafui; Carlson, DavidFactor models are routinely used for dimensionality reduction in modeling of correlated, high-dimensional data. We are particularly motivated by neuroscience applications collecting high-dimensional `predictors' corresponding to brain activity in different regions along with behavioral outcomes. Joint factor models for the predictors and outcomes are natural, but maximum likelihood estimates of these models can struggle in practice when there is model misspecification. We propose an alternative inference strategy based on supervised autoencoders; rather than placing a probability distribution on the latent factors, we define them as an unknown function of the high-dimensional predictors. This mapping function, along with the loadings, can be optimized to explain variance in brain activity while simultaneously being predictive of behavior. In practice, the mapping function can range in complexity from linear to more complex forms, such as splines or neural networks, with the usual tradeoff between bias and variance. This approach yields distinct solutions from a maximum likelihood inference strategy, as we demonstrate by deriving analytic solutions for a linear Gaussian factor model. Using synthetic data, we show that this function-based approach is robust against multiple types of misspecification. We then apply this technique to a neuroscience application resulting in substantial gains in predicting behavioral tasks from electrophysiological measurements in multiple factor models.Item Open Access The Application of Ocean Zoning Management for Offshore Energy Development in North Carolina(2009-04-23T17:35:14Z) Carlson, DavidThe concept of spatial planning, or zoning, is widely applied for regulating land use activities. This project assesses the potential for using ocean zoning as a management tool in North Carolina. In particular, this project looks at the role of new offshore energy developments, such as wind farms, and how management policies may adapt to handle these projects. Ocean Zoning has been successfully applied in the Great Barrier Reef Marine Park and the Florida Keys National Marine Sanctuary. Zones are designated based on their biological and physical properties. Activities within each zone are classified as compatible, conditionally compatible, or incompatible and are permitted based on their classification and the overall management objectives. For this project, a survey of current users of the North Carolina coastal community was conducted to gather data on the variety of activities in the North Carolina coastal zone and the user’s opinions on compatibility of 13 different activities. These results were compiled into a compatibility matrix to guide classification of activities. Based on this matrix of responses, conservation and planning are clearly perceived as activities benefiting the activities of all respondents. Conversely, minerals mining and coastal development are perceived as harmful to all respondents activities. The apparent compatibility of other activities varies by respondent and activity.