Hierarchical Inference Research Articles

Dynamics of intersexual dominance in a highly dimorphic primate

Intersexual dominance, which is measured by the probability that members of one sex elicit submission of members of the other sex during agonistic interactions, is often skewed in favor of males. However, even in sexually dimorphic species, several factors may influence intersexual dominance. Here, we use an 8-year dataset to examine the dynamics of intersexual dominance in wild-living mandrills (Mandrillus sphinx). Mandrills exhibit an extreme male-biased sexual size dimorphism but females show pronounced kin-differentiated social relationships and occasionally form coalitions against males. We established intersexual hierarchies across consecutive 6-month time blocks, representing either mating or birth seasons. Although females appeared to outrank 11% of males, they elicited male submission in only 2% of agonistic interactions against males. This discrepancy is likely due to the temporary residency of most males in the exceptionally large mandrill groups, the sexually coercive male mating strategies and the scarce number of agonistic interactions within most dyads, that may limit hierarchical inferences. In a second step, we found that the intersexual hierarchy mixes the intrasexual ones respecting their respective order. Females outranked mostly young and old males during the mating (vs. birth) season and social integration was positively correlated to dominance status in both sexes. In a third step, we found that females win more conflicts against young or old males which are closer to them in the intersexual hierarchy. These results extend our understanding of female-male dominance relationships by indicating that female mandrills occasionally outrank males who are considerably larger than them, and that a combination of demographic and social factors can influence the intersexual hierarchy.

Visual motion perception as online hierarchical inference

Identifying the structure of motion relations in the environment is critical for navigation, tracking, prediction, and pursuit. Yet, little is known about the mental and neural computations that allow the visual system to infer this structure online from a volatile stream of visual information. We propose online hierarchical Bayesian inference as a principled solution for how the brain might solve this complex perceptual task. We derive an online Expectation-Maximization algorithm that explains human percepts qualitatively and quantitatively for a diverse set of stimuli, covering classical psychophysics experiments, ambiguous motion scenes, and illusory motion displays. We thereby identify normative explanations for the origin of human motion structure perception and make testable predictions for future psychophysics experiments. The proposed online hierarchical inference model furthermore affords a neural network implementation which shares properties with motion-sensitive cortical areas and motivates targeted experiments to reveal the neural representations of latent structure.

EE647 Real-Word Effectiveness and Cost Consequence of Antipsychotic Treatment Choices in the Treatment of Schizophrenia in Italy: A Bayesian Hierarchical Inference Model

EE647 Real-Word Effectiveness and Cost Consequence of Antipsychotic Treatment Choices in the Treatment of Schizophrenia in Italy: A Bayesian Hierarchical Inference Model

Structure learning enhances concept formation in synthetic Active Inference agents.

Humans display astonishing skill in learning about the environment in which they operate. They assimilate a rich set of affordances and interrelations among different elements in particular contexts, and form flexible abstractions (i.e., concepts) that can be generalised and leveraged with ease. To capture these abilities, we present a deep hierarchical Active Inference model of goal-directed behaviour, and the accompanying belief update schemes implied by maximising model evidence. Using simulations, we elucidate the potential mechanisms that underlie and influence concept learning in a spatial foraging task. We show that the representations formed-as a result of foraging-reflect environmental structure in a way that is enhanced and nuanced by Bayesian model reduction, a special case of structure learning that typifies learning in the absence of new evidence. Synthetic agents learn associations and form concepts about environmental context and configuration as a result of inferential, parametric learning, and structure learning processes-three processes that can produce a diversity of beliefs and belief structures. Furthermore, the ensuing representations reflect symmetries for environments with identical configurations.

Deep learning and Bayesian inference of gravitational-wave populations: Hierarchical black-hole mergers

The catalog of gravitational-wave events is growing, and so are our hopes of constraining the underlying astrophysics of stellar-mass black-hole mergers by inferring the distributions of, e.g., masses and spins. While conventional analyses parametrize this population with simple phenomenological models, we propose an emulation-based approach that can compare astrophysical simulations against gravitational-wave data. We combine state-of-the-art deep-learning techniques with hierarchical Bayesian inference and exploit our approach to constrain the properties of repeated black-hole mergers from the gravitational-wave events in the most recent LIGO/Virgo catalog. Deep neural networks allow us to (i) construct a flexible single-channel population model that accurately emulates simple parametrized numerical simulations of hierarchical mergers, (ii) estimate selection effects, and (iii) recover the branching ratios of repeated-merger generations. Among our results, we find the following: The distribution of host-environment escape speeds favors values less than $100~\mathrm{km\,s^{-1}}$ but is relatively flat, with around $37\%$ of first-generation mergers retained in their host environments; first-generation black holes are born with a maximum mass that is compatible with current estimates from pair-instability supernovae; there is multimodal substructure in both the mass and spin distributions, which, in our model, can be explained by repeated mergers; and binaries with a higher-generation component make up at least $14\%$ of the underlying population. Though these results are inferred through emulation of a simplified model, the deep-learning pipeline we present is readily applicable to realistic astrophysical simulations

Hierarchical Bayesian LSTM for Head Trajectory Prediction on Omnidirectional Images

When viewing omnidirectional images (ODIs), viewers can access different viewports via head movement (HM), which sequentially forms head trajectories in spatial-temporal domain. Thus, head trajectories play a key role in modeling human attention on ODIs. In this paper, we establish a large-scale dataset collecting 21,600 head trajectories on 1,080 ODIs. By mining our dataset, we find two important factors influencing head trajectories, i.e., temporal dependency and subject-specific variance. Accordingly, we propose a novel approach integrating hierarchical Bayesian inference into long short-term memory (LSTM) network for head trajectory prediction on ODIs, which is called HiBayes-LSTM. In HiBayes-LSTM, we develop a mechanism of Future Intention Estimation (FIE), which captures the temporal correlations from previous, current and estimated future information, for predicting viewport transition. Additionally, a training scheme called Hierarchical Bayesian inference (HBI) is developed for modeling inter-subject uncertainty in HiBayes-LSTM. For HBI, we introduce a joint Gaussian distribution in a hierarchy, to approximate the posterior distribution over network weights. By sampling subject-specific weights from the approximated posterior distribution, our HiBayes-LSTM approach can yield diverse viewport transition among different subjects and obtain multiple head trajectories. Extensive experiments validate that our HiBayes-LSTM approach significantly outperforms 9 state-of-the-art approaches for trajectory prediction on ODIs, and then it is successfully applied to predict saliency on ODIs.

Bayesian WIMP detection with the Cherenkov Telescope Array

Over the past decades Bayesian methods have become increasingly popular in astronomy and physics as stochastic samplers have enabled efficient investigation of high-dimensional likelihood surfaces.In this work we develop a hierarchical Bayesian inference framework to detect the presence of dark matter annihilation events in data from the Cherenkov Telescope Array (CTA). Gamma-ray events are weighted based on their measured sky position Ω̂ m and energy Em in order to derive a posterior distribution for the dark matter's velocity averaged cross section 〈σv〉. The dark matter signal model and the astrophysical background model are cast as prior distributions for (Ω̂ m , Em ). The shape of these prior distributions can be fixed based on first-principle models; or one may adopt flexible priors to include theoretical uncertainty, for example, in the dark matter annihilation spectrum or the astrophysical distribution of sky location. We demonstrate the utility of this formalism using simulated data with a Galactic Centre signal from scalar singlet dark-matter model. The sensitivity according to our method is comparable to previous estimates of the CTA sensitivity.

WGDI: A user-friendly toolkit for evolutionary analyses of whole-genome duplications and ancestral karyotypes

Evidence of whole-genome duplications (WGDs) and subsequent karyotype changes has been detected in most major lineages of living organisms on Earth. To clarify the complex resulting multi-layered patterns of gene collinearity in genome analyses, there is a need for convenient and accurate toolkits. To meet this need, we developed WGDI (Whole-Genome Duplication Integrated analysis), a Python-based command-line tool that facilitates comprehensive analysis of recursive polyploidization events and cross-species genome alignments. WGDI supports three main workflows (polyploid inference, hierarchical inference of genomic homology, and ancestral chromosome karyotyping) that can improve the detection of WGD and characterization of WGD-related events based on high-quality chromosome-level genomes. Significantly, it can extract complete synteny blocks and facilitate reconstruction of detailed karyotype evolution. This toolkit is freely available at GitHub (https://github.com/SunPengChuan/wgdi). As an example of its application, WGDI convincingly clarified karyotype evolution in Aquilegia coerulea and Vitis vinifera following WGDs and rejected the hypothesis that Aquilegia contributed as a parental lineage to the allopolyploid origin of core dicots.

HVAE: A deep generative model via hierarchical variational auto-encoder for multi-view document modeling

With the widespread development of the internet, multi-view text documents have become increasingly common, which has led to extensive research on multi-view text document modeling. As opposed to traditional single-view document modeling, which treats each document independently and learns each document as a single topic representation, the views of multi-view text documents have complicated correlation relationships that include both the global and local underlying topical information. In this study, we introduce a deep generative model for multi-view document modeling known as Hierarchical Variational Auto-Encoder (HVAE), which combines the advantages of the probability generative model for learning interpretable latent information and the deep neural network for efficient parameter inference. Specifically, a set of hierarchical topic representations is learned for each multi-view document to capture the document-level global topical information and view-level local topical information for each view. A two-level hierarchical topic inference network is investigated as the encoder network of HVAE, which is designed using an aligned variational auto-encoder, to learn the hierarchical topic representations. Subsequently, multi-view documents are generated through a two-layered generation network, considering both the view-level local and document-level global topic representations. Experiments on three real datasets of different scales for various tasks demonstrate the satisfactory results of the proposed method.

A New Configuration Method for Glass Substrate Transfer Robot Modules Based on Kansei Engineering

How to effectively match the relationship between users’ perceptual demands and the characteristics of industrial robot modules becomes a pressing issue when perceptual demands become a significant determinant of whether users purchase and employ industrial robots. In this regard, we propose a Kansei Engineering-based method for industrial robot module configuration, using the module design of a glass substrate transfer robot as an example. First, the method analyzes the perceptual demand characteristics of the target user, utilizing the semantic difference method, and then establishes a mapping relationship between the user’s perceptual demand and the robot design elements, utilizing the hierarchical inference method. On the basis of this mapping relationship, the robot module for transfer glass substrates is then designed. Finally, orthogonal design and conjoint analysis were used to effectively and objectively analyze user preferences for various module configuration alternatives. The results indicate that the industrial robot’s shape, color, and material are the three appearance characteristics that influence the user’s perceptual demands. The slender, rigid design features of the industrial robot, such as the streamlined drive shaft, lengthwise expanded body structure, integrated body structure, and hidden plugs, as well as the simple color scheme and smooth metal surface, are key elements in the industrial robot’s perceptual design. The turn shaft module and lift shaft module have respective weights of 35.040% and 31.120%, determining whether the glass substrate transfer robot can create a simple style. In the context of the widespread use of industrial robot modules, the methods and findings of this study offer new ideas for the design of industrial robot modules and broaden the research and applications of Kansei Engineering in module design.

Inferring binary black holes stellar progenitors with gravitational wave sources

ABSTRACT With its last observing run, the LIGO, Virgo, and KAGRA collaboration has detected almost one hundred gravitational waves from compact binary coalescences. A common approach to studying the population properties of the observed binaries is to use phenomenological models to describe the spin, mass, and redshift distributions. More recently, with the aim of providing a clearer link to astrophysical processes forming the observed compact binaries coalescences, several authors have proposed to employ synthetic catalogues for population studies. In this paper, we review how to employ and interpret synthetic binary catalogues for gravitational-wave progenitors studies. We describe how to build multichannel merger rates and describe their associated probabilities focusing on stellar progenitor properties. We introduce a method to quantify the match between the phenomenological reconstruction of merger rates with synthetic catalogues. We detail the implementation of synthetic catalogues for multichannel hierarchical Bayesian inference, highlighting computational aspects and issues related to hyper-prior choice. We find that when inferring stellar progenitors’ properties from gravitational-wave observations, the relative efficiency in compact objects production should be taken into account. Finally, by simulating binary black hole detections with LIGO and Virgo sensitivity expected for the O4 observing run, we present two case studies related to the inference of the common envelope efficiency and progenitor metallicity of the binary black holes. We finally discuss how progenitors’ properties can be linked to binary black hole properties.

Improving Estimates and Change Detection of Forest Above-Ground Biomass Using Statistical Methods

Forests store approximately as much carbon as is in the atmosphere, with potential to take in or release carbon rapidly based on growth, climate change and human disturbance. Above-ground biomass (AGB) is the largest carbon pool in most forest systems, and the quickest to change following disturbance. Quantifying AGB on a global scale and being able to reliably map how it is changing, is therefore required for tackling climate change by targeting and monitoring policies. AGB can be mapped using remote sensing and machine learning methods, but such maps have high uncertainties, and simply subtracting one from another does not give a reliable indication of changes. To improve the quantification of AGB changes it is necessary to add advanced statistical methodology to existing machine learning and remote sensing methods. This review discusses the areas in which techniques used in statistical research could positively impact AGB quantification. Nine global or continental AGB maps, and a further eight local AGB maps, were investigated in detail to understand the limitations of techniques currently used. It was found that both modelling and validation of maps lacked spatial consideration. Spatial cross validation or other sampling methods, which specifically account for the spatial nature of this data, are important to introduce into AGB map validation. Modelling techniques which capture the spatial nature should also be used. For example, spatial random effects can be included in various forms of hierarchical statistical models. These can be estimated using frequentist or Bayesian inference. Strategies including hierarchical modelling, Bayesian inference, and simulation methods can also be applied to improve uncertainty estimation. Additionally, if these uncertainties are visualised using pixelation or contour maps this could improve interpretation. Improved uncertainty, which is commonly between 30% and 40%, is in addition needed to produce accurate change maps which will benefit policy decisions, policy implementation, and our understanding of the carbon cycle.

Generalized Cross-Severity Fault Diagnosis of Bearings via a Hierarchical Cross-Category Inference Framework

Data-driven fault diagnosis primarily involves the identification of different fault locations and fault severities. Focusing on a challenging task for which the target fault severities do not exist in the training samples, this article proposes a generalized cross-severity bearing fault diagnosis scheme based on a novel hierarchical cross-category inference framework. The proposed method uses an outlier detection scheme based on unsupervised feature mapping and local outlier probability calculation to identify the unseen samples. A neural network embedded with a tree-structured decision layer acts as a backbone to execute fault diagnosis at different hierarchies for different sample types, seen or unseen. Additionally, the metric learning method is used to support the approximate severity inference of the unseen samples after the fault locations are identified in the hierarchical model. Experiments performed on an aeronautical bearing test rig revealed that the proposed scheme is both feasible and superior to existing methods.

Emotion dynamics as hierarchical Bayesian inference in time.

What fundamental property of our environment would be most valuable and optimal in characterizing the emotional dynamics we experience in daily life? Empirical work has shown that an accurate estimation of uncertainty is necessary for our optimal perception, learning, and decision-making. However, the role of this uncertainty in governing our affective dynamics remains unexplored. Using Bayesian encoding, decoding and computational modeling, on a large-scale neuroimaging and behavioral data on a passive movie-watching task, we showed that emotions naturally arise due to ongoing uncertainty estimations about future outcomes in a hierarchical neural architecture. Several prefrontal subregions hierarchically encoded a lower-dimensional signal that highly correlated with the evolving uncertainty. Crucially, the lateral orbitofrontal cortex (lOFC) tracked the temporal fluctuations of this uncertainty and was predictive of the participants' predisposition to anxiety. Furthermore, we observed a distinct functional double-dissociation within OFC with increased connectivity between medial OFC and DMN, while with that of lOFC and FPN in response to the evolving affect. Finally, we uncovered a temporally predictive code updating an individual's beliefs spontaneously with fluctuating outcome uncertainty in the lOFC. A biologically relevant and computationally crucial parameter in the theories of brain function, we propose uncertainty to be central to the definition of complex emotions.

Comparing Bayes factors and hierarchical inference for testing general relativity with gravitational waves

In the context of testing general relativity with gravitational waves, constraints obtained with multiple events are typically combined either through a hierarchical formalism or though a combined multiplicative Bayes factor. We show that the well-known dependence of Bayes factors on the analysis priors in regions of the parameter space without likelihood support can lead to strong confidence in favor of incorrect conclusions when one employs the multiplicative Bayes factor. Bayes factors $\mathcal{O}(1)$ are ambivalent as they depend sensitively on the analysis priors, which are rarely set in a principled way; additionally, combined Bayes factors $>\mathcal{O}({10}^{3})$ can be obtained in favor of the incorrect conclusion depending on the analysis priors when many $\mathcal{O}(1)$ Bayes factors are multiplied, and specifically when the priors are much wider than the underlying population. The hierarchical analysis that instead infers the ensemble distribution of the individual beyond-general-relativity constraints does not suffer from this problem, and generically converges to favor the correct conclusion. Rather than a naive multiplication, a more reliable Bayes factor can be computed from the hierarchical analysis. We present a number of toy models showing that the practice of multiplying Bayes factors can lead to incorrect conclusions.

Context-Aware Multi-Criteria Handover at the Software Defined Network Edge for Service Differentiation in Next Generation Wireless Networks

The densified deployment of heterogeneous networks coexisting with a variety of overlapping cells has emerged as a viable solution for next generation wireless networks. Despite numerous advantages, the heterogeneity and denseness also raise complicated handover management issue. Nonetheless, most existing handover methods generally depend on one or more objective attributes, and rarely consider the subjective demands of personalized users and specific applications that demand differentiated services. Through decomposing the control plane and data plane, software defined network(SDN) offers a flexible architectural paradigm to overcome these challenges. In this article, we first develop an SDN-driven handover architecture that is capable of perceiving global network status and requirements from various perspectives, including the physical layer, users, and applications. Then, a context-aware multi-criteria handover mechanism is developed in the SDN edge to provide differentiated services. Considering the numerous complicated factors, the handover decision is made based on a hierarchical fuzzy inference system to process diverse attributes and vague requirements described in natural language. Finally, we evaluate the performance of our proposed scheme through a combination of extensive simulations and real-world experiments. The results demonstrate that our solution outperforms the baseline handover schemes, more efficiently providing differentiated services with respect to throughput, bandwidth cost, and application satisfaction, and is efficient and feasible in practice.

A Bayesian framework for calibration of multiaxial fatigue curves

A Bayesian framework is proposed to re-formulate a multiaxial fatigue model and produce probabilistic stress-life fatigue curves from experimental data. The proposed framework identifies the experimentally-driven parameters governing the multiaxial fatigue model, in the form of probability distributions. Classical and hierarchical Bayesian inference strategies are presented, accompanied by rigorous analytical expressions for calculating the joint posterior distributions necessary for in-field implementation. An example illustrates the application of the proposed hierarchical Bayesian inference framework and how it compares to a deterministic approach. This probabilistic treatment makes the existing fatigue models suitable for exercising uncertainty propagation for reliability analysis and design purposes.

A novel hierarchical fuzzy inference system for supplier selection and performance improvement in the oil & gas industry

ABSTRACT Evaluation of suppliers is essential to increasing competitive power, customer satisfaction, and profitability. Oil and gas companies can use this research to evaluate suppliers and map the potential path forward for future collaborations. Six supply chain managers in Iran designed HFIS for the oil and gas industry. Shannon Entropy was used to determine the relative weights of suppliers concerning overall uncertainty because the Oil and Gas industry uses many unstructured Key Performance Indicators (KPIs). Using Matlab Toolbox FIS, a future cooperation roadmap was developed. Experts suggested future collaboration with certain suppliers based on the HFIS results. The future cooperation strategy proposed by the framework is highly in line with their expectations. FIS results indicate that the proposed can help select the most appropriate suppliers for cooperation while providing a roadmap for weaker suppliers to improve their performance.

Hierarchical inference as a source of human biases.

The finding that human decision-making is systematically biased continues to have an immense impact on both research and policymaking. Prevailing views ascribe biases to limited computational resources, which require humans to resort to less costly resource-rational heuristics. Here, we propose that many biases in fact arise due to a computationally costly way of coping with uncertainty-namely, hierarchical inference-which by nature incorporates information that can seem irrelevant. We show how, in uncertain situations, Bayesian inference may avail of the environment's hierarchical structure to reduce uncertainty at the cost of introducing bias. We illustrate how this account can explain a range of familiar biases, focusing in detail on the halo effect and on the neglect of base rates. In each case, we show how a hierarchical-inference account takes the characterization of a bias beyond phenomenological description by revealing the computations and assumptions it might reflect. Furthermore, we highlight new predictions entailed by our account concerning factors that could mitigate or exacerbate bias, some of which have already garnered empirical support. We conclude that a hierarchical inference account may inform scientists and policy makers with a richer understanding of the adaptive and maladaptive aspects of human decision-making.

Neural correlates of transitive inference: An SDM meta-analysis on 32 fMRI studies

Transitive inference (TI) is a critical capacity involving the integration of relevant information into prior knowledge structure for drawing novel inferences on unobserved relationships. To date, the neural correlates of TI remain unclear due to the small sample size and heterogeneity of various experimental tasks from individual studies. Here, the meta-analysis on 32 fMRI studies was performed to detect brain activation patterns of TI and its three paradigms (spatial inference, hierarchical inference, and associative inference). We found the hippocampus, prefrontal cortex (PFC), putamen, posterior parietal cortex (PPC), retrosplenial cortex (RSC), supplementary motor area (SMA), precentral gyrus (PreCG), and median cingulate cortex (MCC) were engaged in TI. Specifically, the RSC was implicated in the associative inference, whereas PPC, SMA, PreCG, and MCC were implicated in the hierarchical inference. In addition, the hierarchical inference and associative inference both evoked activation in the hippocampus, medial PFC, and PCC. Although the meta-analysis on spatial inference did not generate a reliable result due to insufficient amount of investigations, the present work still offers a new insight for better understanding the neural basis underlying TI.