
Learning from lions: inferring the utility of agents from their trajectories
We build a model using Gaussian processes to infer a spatiotemporal vector field from observed agent trajectories. Significant landmarks or influence points in agent surroundings are jointly derived through vector calculus operations that indicate presence of sources and sinks. We evaluate these influence points by using the KullbackLeibler divergence between the posterior and prior Laplacian of the inferred spatiotemporal vector field. Through locating significant features that influence trajectories, our model aims to give greater insight into underlying causal utility functions that determine agent decisionmaking. A key feature of our model is that it infers a joint Gaussian process over the observed trajectories, the timevarying vector field of utility and canonical vector calculus operators. We apply our model to both synthetic data and lion GPS data collected at the Bubye Valley Conservancy in southern Zimbabwe.
09/07/2017 ∙ by Adam D. Cobb, et al. ∙ 0 ∙ shareread it

LossCalibrated Approximate Inference in Bayesian Neural Networks
Current approaches in approximate inference for Bayesian neural networks minimise the KullbackLeibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application, and therefore cannot guarantee optimal predictions for a given task. To make more suitable taskspecific approximations, we introduce a new losscalibrated evidence lower bound for Bayesian neural networks in the context of supervised learning, informed by Bayesian decision theory. By introducing a lower bound that depends on a utility function, we ensure that our approximation achieves higher utility than traditional methods for applications that have asymmetric utility functions. Furthermore, in using dropout inference, we highlight that our new objective is identical to that of standard dropout neural networks, with an additional utilitydependent penalty term. We demonstrate our new losscalibrated model with an illustrative medical example and a restricted model capacity experiment, and highlight failure modes of the comparable weighted cross entropy approach. Lastly, we demonstrate the scalability of our method to real world applications with perpixel semantic segmentation on an autonomous driving data set.
05/10/2018 ∙ by Adam D. Cobb, et al. ∙ 0 ∙ shareread it

Identifying Sources and Sinks in the Presence of Multiple Agents with Gaussian Process Vector Calculus
In systems of multiple agents, identifying the cause of observed agent dynamics is challenging. Often, these agents operate in diverse, nonstationary environments, where models rely on handcrafted environmentspecific features to infer influential regions in the system's surroundings. To overcome the limitations of these inflexible models, we present GPLAPLACE, a technique for locating sources and sinks from trajectories in timevarying fields. Using Gaussian processes, we jointly infer a spatiotemporal vector field, as well as canonical vector calculus operations on that field. Notably, we do this from only agent trajectories without requiring knowledge of the environment, and also obtain a metric for denoting the significance of inferred causal features in the environment by exploiting our probabilistic method. To evaluate our approach, we apply it to both synthetic and realworld GPS data, demonstrating the applicability of our technique in the presence of multiple agents, as well as its superiority over existing methods.
02/22/2018 ∙ by Adam D. Cobb, et al. ∙ 0 ∙ shareread it

Bayesian Deep Learning for Exoplanet Atmospheric Retrieval
Over the past decade, the study of exoplanets has shifted from their detection to the characterization of their atmospheres. Atmospheric retrieval, the inverse modeling technique used to determine an atmosphere's temperature and composition from an observed spectrum, is both timeconsuming and computeintensive, requiring complex algorithms that compare thousands to millions of atmospheric models to the observational data to find the most probable values and associated uncertainties for each model parameter. For rocky, terrestrial planets, the retrieved atmospheric composition can give insight into the surface fluxes of gaseous species necessary to maintain the stability of that atmosphere, which may in turn provide insight into the geological and/or biological processes active on the planet. These atmospheres contain many molecules, some of which are biosignatures, or molecules indicative of biological activity. Runtimes of traditional retrieval models scale with the number of model parameters, so as more molecular species are considered, runtimes can become prohibitively long. Recent advances in machine learning (ML) and computer vision offer new ways to reduce the time to perform a retrieval by orders of magnitude, given a sufficient data set to train with. Here we present an MLbased retrieval framework called Intelligent exoplaNet Atmospheric RetrievAl (INARA) that consists of a Bayesian deep learning model for retrieval and a data set of 3,000,000 spectra of synthetic rocky exoplanets generated using the NASA Planetary Spectrum Generator (PSG). Our work represents the first ML model for rocky, terrestrial exoplanets and the first synthetic data set of spectra generated at this scale.
11/08/2018 ∙ by Frank Soboczenski, et al. ∙ 0 ∙ shareread it

Bayesian deep neural networks for lowcost neurophysiological markers of Alzheimer's disease severity
As societies around the world are ageing, the number of Alzheimer's disease (AD) patients is rapidly increasing. To date, no lowcost, noninvasive biomarkers have been established to advance the objectivization of AD diagnosis and progression assessment. Here, we utilize Bayesian neural networks to develop a multivariate predictor for AD severity using a wide range of quantitative EEG (QEEG) markers. The Bayesian treatment of neural networks both automatically controls model complexity and provides a predictive distribution over the target function, giving uncertainty bounds for our regression task. It is therefore well suited to clinical neuroscience, where data sets are typically sparse and practitioners require a precise assessment of the predictive uncertainty. We use data of one of the largest prospective AD EEG trials ever conducted to demonstrate the potential of Bayesian deep learning in this domain, while comparing two distinct Bayesian neural network approaches, i.e., Monte Carlo dropout and Hamiltonian Monte Carlo.
12/12/2018 ∙ by Wolfgang Fruehwirt, et al. ∙ 0 ∙ shareread it

An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval
Machine learning is now used in many areas of astrophysics, from detecting exoplanets in Kepler transit signals to removing telescope systematics. Recent work demonstrated the potential of using machine learning algorithms for atmospheric retrieval by implementing a random forest to perform retrievals in seconds that are consistent with the traditional, computationallyexpensive nestedsampling retrieval method. We expand upon their approach by presenting a new machine learning model, plannet, based on an ensemble of Bayesian neural networks that yields more accurate inferences than the random forest for the same data set of synthetic transmission spectra. We demonstrate that an ensemble provides greater accuracy and more robust uncertainties than a single model. In addition to being the first to use Bayesian neural networks for atmospheric retrieval, we also introduce a new loss function for Bayesian neural networks that learns correlations between the model outputs. Importantly, we show that designing machine learning models to explicitly incorporate domainspecific knowledge both improves performance and provides additional insight by inferring the covariance of the retrieved atmospheric parameters. We apply plannet to the Hubble Space Telescope Wide Field Camera 3 transmission spectrum for WASP12b and retrieve an isothermal temperature and water abundance consistent with the literature. We highlight that our method is flexible and can be expanded to higherresolution spectra and a larger number of atmospheric parameters.
05/25/2019 ∙ by Adam D. Cobb, et al. ∙ 0 ∙ shareread it
Adam D. Cobb
is this you? claim profile