Article
Engineering, Geological
Wenmin Yao, Changdong Li, Changbin Yan, Hongbin Zhan
Summary: The study proposes a hybrid framework for slope reliability based on Bayesian sequential updating technology, integrating prior knowledge, multiple estimation methods, and model uncertainties to estimate slope reliability with limited geotechnical data. Through experiments with three slope examples, the framework is shown to provide reliable and accurate estimations of slope reliability.
Article
Construction & Building Technology
Shima Taheri, R. Karami Mohammadi
Summary: This research presents a novel method for sequential ground motion selection based on Bayesian updating approach in probabilistic prediction of seismic demand parameters. The method directly chooses ground motions through a probabilistic evaluation of structural responses. It achieves an approximation of a large number of nonlinear analyses using a limited number of linear analysis results. The proposed method is efficient and independent of hazard level or building height, showing significant improvements in computing efficiency and risk assessment.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Astronomy & Astrophysics
Daria Gangardt, Davide Gerosa, Michael Kesden, Viola De Renzis, Nathan Steinle
Summary: In this study, we investigate the detectability of subdominant spin effects in merging black-hole binaries using current gravitational-wave data. We present constraints on the resulting amplitudes and frequencies by separating the spin dynamics into precession and nutation. Furthermore, we explore the current constraints on spin morphologies and use a sequential prior conditioning approach to dissect weak effects from the signals. For the current events, we find no significant measurements of weak spin effects. However, synthesizing a source with high nutational amplitude shows that future detections may provide powerful constraints, indicating the potential to detect spin nutations in gravitational-wave data.
Article
Mathematics
Jose Manuel Gutierrez
Summary: The conditional probability formula accurately updates probability assignments when new information is added. It is proven that this formula is the only transformed probability measure that satisfies the minimum requirement relational assumption, using a non-atomic probability measure. This result is applicable to the standard Bayesian parametric model.
REVISTA DE LA REAL ACADEMIA DE CIENCIAS EXACTAS FISICAS Y NATURALES SERIE A-MATEMATICAS
(2023)
Article
Engineering, Multidisciplinary
Hening Huang
Summary: This paper proposes a propensity-based framework for measurement uncertainty analysis. The measurand is regarded as a random variable characterized by central tendency and dispersion. The state of propensity is described by a probability density function (PDF). The framework encodes the state of propensity of the measurand based on all available information about influence quantities.
Article
Physics, Multidisciplinary
Samuel Kessler, Adam Cobb, Tim G. J. Rudner, Stefan Zohren, Stephen J. Roberts
Summary: Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting and provide an informative prior. However, applying this approach to Bayesian neural networks fails to prevent forgetting, highlighting the limitations of sequential Bayesian inference in neural networks. Moreover, model misspecification and task data imbalances can also contribute to sub-optimal continual learning performance.
Article
Engineering, Multidisciplinary
Yong Huang, James L. Beck, Hui Li, Yulong Ren
Summary: The study introduces a sequential SBL framework for recursive learning of sparse vectors, which can effectively estimate the marginal posterior distribution of the parameter vector and improve the performance of sparse Bayesian learning.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2021)
Article
Biology
Jan Boelts, Jan-Matthis Lueckmann, Richard Gao, Jakob H. Macke
Summary: Inferring parameters of computational models is crucial in cognitive neuroscience. Simulation-based inference (SBI) using neural density estimators provides a more efficient way to capture decision-making data. Compared to traditional methods, this approach demonstrates higher accuracy and training efficiency.
Article
Pharmacology & Pharmacy
Andrew P. Grieve
Summary: This article extends the use of probability of success calculations to group sequential designs and discusses how knowledge about interim analysis results can influence the assessment of study's probability of success.
PHARMACEUTICAL STATISTICS
(2023)
Article
Computer Science, Theory & Methods
Lisa Gaedke-Merzhaeuser, Janet van Niekerk, Olaf Schenk, Havard Rue
Summary: This work presents parallelization strategies for the methodology of integrated nested Laplace approximations (INLA) to meet the growing demand of larger-scale Bayesian inference tasks. The introduced approach leverages nested thread-level parallelism, robust regression and state-of-the-art sparse linear solver PARDISO, resulting in significant speedups in various real-world applications. The improved parallelization scheme is already integrated into the open-source R-INLA package for convenient use.
STATISTICS AND COMPUTING
(2023)
Editorial Material
Biology
Christopher R. Fetsch, Uta Noppeney
Summary: Sensory systems have evolved to provide organisms with information about the environment. It is important to consider perception and sensorimotor behavior as multi-modal, as each sense provides complementary information about the same world. This article highlights recent advances in understanding the higher order aspects of multisensory processing.
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES
(2023)
Article
Management
Emmanuel C. Mamatzakis, Mike G. Tsionas
Summary: This study proposes a novel approach to identify happiness for British households using latent model frontier analysis with longitudinal data, employing Bayesian inference and particle filtering techniques to estimate happiness efficiency. Results suggest that happiness efficiency is related to welfare loss from potential resource misuse, with agreeable and extravert personality traits enhancing happiness efficiency, while neuroticism impairs it.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Mathematics
Nasser Madani
Summary: Sequential indicator simulation is a popular algorithm for modeling geological features, but its ability to capture long-range geological features has been a topic of debate. This study proposes an improved Bayesian sequential indicator simulation approach that incorporates soft data and assigns weights to their probabilities. Experimental results demonstrate that this method outperforms other techniques in reproducing long-range geological features while maintaining consistency with other statistical measures.
Article
Multidisciplinary Sciences
Celia C. Beron, Shay Q. Neufeld, Scott W. Linderman, Bernardo L. Sabatini
Summary: In probabilistic and nonstationary environments, mice use internal and external cues to make decisions. The behavior of mice in a task with time-varying reward probabilities is both deterministic and stochastic. Modeling their behavior through equivalent models reveals that mice achieve near-maximal reward rates.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Engineering, Electrical & Electronic
Chenhao Li, Simon Godsill
Summary: The non-homogeneous Poisson process allows the intensity of point generation to vary across time or space domains, with applications in signal processing and machine learning but limited by intractable likelihood function and computationally efficient inference schemes. This paper proposes a framework that combines non-homogeneous Poisson model with continuous-time state-space models for efficient online inference. The proposed approach shows improved performance and computational efficiency compared to batch-based competitor algorithm and a simple baseline kernel estimation scheme.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2021)
Article
Neurosciences
Zachary P. Kilpatrick, William R. Holmes, Tahra L. Eissa, Kresimir Josic
CURRENT OPINION IN NEUROBIOLOGY
(2019)
Article
Mathematical & Computational Biology
Nicholas W. Barendregt, Kresimir Josic, Zachary P. Kilpatrick
JOURNAL OF COMPUTATIONAL NEUROSCIENCE
(2019)
Article
Mathematical & Computational Biology
Yunjiao Wang, Zachary P. Kilpatrick, Kresimir Josic
JOURNAL OF COMPUTATIONAL NEUROSCIENCE
(2020)
Article
Physics, Multidisciplinary
Bhargav Karamched, Megan Stickler, William Ott, Benjamin Lindner, Zachary P. Kilpatrick, Kresimir Josic
PHYSICAL REVIEW LETTERS
(2020)
Article
Biology
Subekshya Bidari, Zachary P. Kilpatrick
Summary: Honey bees make decisions regarding foraging and nest-site selection in groups, and the spatial properties of the hive and the movement of individuals with different beliefs within it affect the rate of information transmission. Research shows that different belief states of individuals in a hive play a crucial role in collective decision-making, influencing the effectiveness of communication and recruitment within the group.
JOURNAL OF MATHEMATICAL BIOLOGY
(2021)
Article
Biology
Kyra Schapiro, Kresimir Josic, Zachary P. Kilpatrick, Joshua Gold
Summary: This study used human psychophysics to examine the impact of working-memory limitations on the accuracy of continuous decision variables. The results suggest that the degradation of the decision variable depends on the strategy used to form it, either as a single value or as multiple values stored in memory.
Article
Biochemical Research Methods
Tahra L. Eissa, Joshua I. Gold, Kresimir Josic, Zachary P. Kilpatrick
Summary: Solutions to challenging inference problems often involve trade-offs between bias and variance. Complex strategies minimize bias but increase variance, while simple strategies minimize variance but increase bias.
PLOS COMPUTATIONAL BIOLOGY
(2022)
Article
Biology
Nicholas W. Barendregt, Joshua Gold, Kresimir Josic, Zachary P. Kilpatrick
Summary: Models based on normative principles have been important for understanding decision-making in the brain. However, their relevance to decisions made under naturalistic, dynamic conditions is unclear. This study introduces a normative model for decisions based on changing contexts and shows that adaptive thresholds outperform static thresholds in accounting for human response times.
Article
Neurosciences
Jesse I. Gilmer, Michael A. Farries, Zachary Kilpatrick, Ioannis Delis, Jeremy D. Cohen, Abigail L. Person
Summary: The cerebellum is crucial for learning motor coordination and other behaviors, and its granule cell layer (GCL) is believed to perform pattern separation to facilitate learning in Purkinje cells (P-cells). However, the relationship between input reformatting and learning has been debated, with different theories emphasizing various pattern separation features.
JOURNAL OF NEUROPHYSIOLOGY
(2023)
Article
Multidisciplinary Sciences
Nicholas W. Barendregt, Emily G. Webb, Zachary P. Kilpatrick
Summary: Optimal designs minimize the number of experimental runs needed for accurate estimation of model parameters, resulting in efficient algorithms that reduce parameter estimate variance. By utilizing adaptive Bayesian inference, we can estimate transition rates of Markov chains, a common class of stochastic process models. Our sequential Bayesian optimal design updates with each observation and can be extended to other models, resulting in lower overall error in parameter estimates.
PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2023)
Article
Physics, Multidisciplinary
Megan Stickler, William Ott, Zachary P. Kilpatrick, Kresimir Josic, Bhargav R. Karamched
Summary: Normative models describe how humans and animals make decisions, and when applied to social groups, it is often assumed that individuals make independent observations. However, individuals typically gather evidence from common sources, and their observations are rarely independent. This study investigates the impact of correlated evidence on decision accuracy for a group of ideal observers who do not exchange information, revealing that decision accuracy depends on temporal decision order.
PHYSICAL REVIEW RESEARCH
(2023)
Article
Biochemical Research Methods
Tahra L. Eissa, Zachary P. Kilpatrick
Summary: Experience shapes our expectations and biases in working memory, and can be explained by neural circuits and activity. The study found that humans display systematic biases in working memory, which are shaped by experience. The results also suggest that the limitations in working memory reflect efficient representations of environmental structure, providing new insights into how humans integrate environmental knowledge into their cognitive strategies.
PLOS COMPUTATIONAL BIOLOGY
(2023)
Article
Physics, Multidisciplinary
Subekshya Bidari, Ahmed El Hady, Jacob D. Davidson, Zachary P. Kilpatrick
Summary: This study develops a mechanistic model to investigate information sharing and decision strategies in group foraging. The study finds that different modes of communication have different effects on foraging efficiency and robustness.
PHYSICAL REVIEW RESEARCH
(2022)
Article
Multidisciplinary Sciences
Zachary P. Kilpatrick, Jacob D. Davidson, Ahmed El Hady
Summary: This study introduces a normative theory of patch foraging decisions, explaining how foraging behaviors emerge in the face of uncertainty. Model foragers statistically infer patch resource yields using Bayesian updating and make decisions to leave a patch when the certainty of patch type or estimated yield falls below a threshold. The duration of uncertainty in resource availability strongly impacts behavioral variables and decision rules determining patch departures.
JOURNAL OF THE ROYAL SOCIETY INTERFACE
(2021)
Article
Mathematics, Applied
Bhargav Karamched, Simon Stolarczyk, Zachary P. Kilpatrick, Kregimir Josic
SIAM JOURNAL ON APPLIED DYNAMICAL SYSTEMS
(2020)