scholarly journals Bayesian Decoder Models with a Discriminative Observation Process

2020 ◽  
Author(s):  
Mohammad R. Rezaei ◽  
Alex E. Hadjinicolaou ◽  
Sydney S. Cash ◽  
Uri T. Eden ◽  
Ali Yousefi
Keyword(s):  
State Space ◽  
Neural Activity ◽  
Model Development ◽  
High Dimensional ◽  
Modeling Framework ◽  
Movement Trajectories ◽  
State Process ◽  
Observation Process ◽  
Space Modeling ◽  
Low Dimensional

AbstractThe Bayesian state-space neural encoder-decoder modeling framework is an established solution to reveal how changes in brain dynamics encode physiological covariates like movement or cognition. Although the framework is increasingly being applied to progress the field of neuroscience, its application to modeling high-dimensional neural data continues to be a challenge. Here, we propose a novel solution that avoids the complexity of encoder models that characterize high-dimensional data as a function of the underlying state processes. We build a discriminative model to estimate state processes as a function of current and previous observations of neural activity. We then develop the filter and parameter estimation solutions for this new class of state-space modeling framework called the “direct decoder” model. We apply the model to decode movement trajectories of a rat in a W-shaped maze from the ensemble spiking activity of place cells and achieve comparable performance to modern decoding solutions, without needing an encoding step in the model development. We further demonstrate how a dynamical auto-encoder can be built using the direct decoder model; here, the underlying state process links the high-dimensional neural activity to the behavioral readout. The dynamical auto-encoder can optimally estimate the low-dimensional dynamical manifold which represents the relationship between brain and behavior.

scholarly journals Estimating Dynamic Signals From Trial Data With Censored Values

2017 ◽  
Vol 1 ◽  
pp. 58-81 ◽  
Author(s):  
Ali Yousefi ◽  
Darin D. Dougherty ◽  
Emad N. Eskandar ◽  
Alik S. Widge ◽  
Uri T. Eden
Keyword(s):  
Censored Data ◽  
Latent Variable ◽  
Statistical Power ◽  
Computationally Efficient ◽  
Behavioral Experiments ◽  
Modeling Framework ◽  
State Process ◽  
Observation Process ◽  
Special Cases ◽  
Space Modeling

Censored data occur commonly in trial-structured behavioral experiments and many other forms of longitudinal data. They can lead to severe bias and reduction of statistical power in subsequent analyses. Principled approaches for dealing with censored data, such as data imputation and methods based on the complete data’s likelihood, work well for estimating fixed features of statistical models but have not been extended to dynamic measures, such as serial estimates of an underlying latent variable over time. Here we propose an approach to the censored-data problem for dynamic behavioral signals. We developed a state-space modeling framework with a censored observation process at the trial timescale. We then developed a filter algorithm to compute the posterior distribution of the state process using the available data. We showed that special cases of this framework can incorporate the three most common approaches to censored observations: ignoring trials with censored data, imputing the censored data values, or using the full information available in the data likelihood. Finally, we derived a computationally efficient approximate Gaussian filter that is similar in structure to a Kalman filter, but that efficiently accounts for censored data. We compared the performances of these methods in a simulation study and provide recommendations of approaches to use, based on the expected amount of censored data in an experiment. These new techniques can broadly be applied in many research domains in which censored data interfere with estimation, including survival analysis and other clinical trial applications.

scholarly journals LSTM-Guided Coaching Assistant for Table Tennis Practice

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4112 ◽  
Author(s):  
Se-Min Lim ◽  
Hyeong-Cheol Oh ◽  
Jaein Kim ◽  
Juwon Lee ◽  
Jooyoung Park
Keyword(s):  
Time Series ◽  
State Space ◽  
Time Series Data ◽  
State Space Model ◽  
Skill Assessment ◽  
Series Data ◽  
High Dimensional ◽  
Table Tennis ◽  
Space Model ◽  
Low Dimensional

Recently, wearable devices have become a prominent health care application domain by incorporating a growing number of sensors and adopting smart machine learning technologies. One closely related topic is the strategy of combining the wearable device technology with skill assessment, which can be used in wearable device apps for coaching and/or personal training. Particularly pertinent to skill assessment based on high-dimensional time series data from wearable sensors is classifying whether a player is an expert or a beginner, which skills the player is exercising, and extracting some low-dimensional representations useful for coaching. In this paper, we present a deep learning-based coaching assistant method, which can provide useful information in supporting table tennis practice. Our method uses a combination of LSTM (Long short-term memory) with a deep state space model and probabilistic inference. More precisely, we use the expressive power of LSTM when handling high-dimensional time series data, and state space model and probabilistic inference to extract low-dimensional latent representations useful for coaching. Experimental results show that our method can yield promising results for characterizing high-dimensional time series patterns and for providing useful information when working with wearable IMU (Inertial measurement unit) sensors for table tennis coaching.

STATE SPACE MODELING OF YEAST GENE EXPRESSION DYNAMICS

2007 ◽  
Vol 05 (01) ◽  
pp. 31-46 ◽  
Author(s):  
OLLI HAAVISTO ◽  
HEIKKI HYÖTYNIEMI ◽  
CHRISTOPHE ROOS
Keyword(s):  
Gene Expression ◽  
State Space ◽  
Dynamic Models ◽  
System Modeling ◽  
Dynamic State ◽  
Yeast Genome ◽  
High Dimensional ◽  
Dimensional System ◽  
Yeast Saccharomyces Cerevisiae ◽  
Space Modeling

Combined interaction of all the genes forms a central part of the functional system of a cell. Thus, especially the data-based modeling of the gene expression network is currently one of the main challenges in the field of systems biology. However, the problem is an extremely high-dimensional and complex one, so that normal identification methods are usually not applicable specially if aiming at dynamic models. We propose in this paper a subspace identification approach, which is well suited for high-dimensional system modeling and the presented modified version can also handle the underdetermined case with less data samples than variables (genes). The algorithm is applied to two public stress-response data sets collected from yeast Saccharomyces cerevisiae. The obtained dynamic state space model is tested by comparing the simulation results with the measured data. It is shown that the identified model can relatively well describe the dynamics of the general stress-related changes in the expression of the complete yeast genome. However, it seems inevitable that more precise modeling of the dynamics of the whole genome would require experiments especially designed for systemic modeling.

scholarly journals Dynamic Cognitive States Predict Individual Variability in Behavior and Modulate with EEG Functional Connectivity during Working Memory

2021 ◽  
Author(s):  
Christine Beauchene ◽  
Thomas T Hinault ◽  
Sridevi Sarma ◽  
Susan Courtney
Keyword(s):  
Functional Connectivity ◽  
Neural Activity ◽  
Model Performance ◽  
Behavioral Model ◽  
Individual Variability ◽  
Modeling Framework ◽  
Large Variability ◽  
Cognitive States ◽  
Space Modeling ◽  
Eeg Functional Connectivity

Short-term fluctuations in strategy, attention, or motivation can cause large variability in cognitive performance across task trials. Typically, this variability is treated as noise when analyzing the relationships among behavior, neural activity, and experimentally structured task rules and stimuli. These relationships are thought to remain consistent over repeatedly administered identical task conditions (e.g. trial types and stimuli) while the variability is assumed to be random and to cancel out when averaged across trials and individuals. We propose that the variability carries important information regarding a participant's internal cognitive states, and could provide insights into both intra- and inter-individual differences in performance and its neural bases. However, these states are difficult to quantify, as they are not directly measurable. Therefore, we use a mathematical, state-space modeling framework to estimate internal cognitive states from measured behavioral data to predict each participant's reaction time fluctuations. We can quantify each participant's sensitivity to different factors (e.g. previous performance or distractions) that were predicted to affect cognitive states, and thus become sources of variability. By including a participant's states in the behavioral model, we improved model performance by a factor of 10, over a model with only experimental task parameters. We show how the participant-specific states reflect neural activity by identifying EEG functional connectivity features that modulate with each state. Overall, this approach could better quantify and characterize both individual and population behavioral differences across time, which could improve understanding of the neural mechanisms underlying the interactions among cognitive, strategic and motivational processes affecting behavior.

Parameter Estimation in Multiple Dynamic Synaptic Coupling Model Using Bayesian Point Process State-Space Modeling Framework

2021 ◽  
pp. 1-31
Author(s):  
Yalda Amidi ◽  
Behzad Nazari ◽  
Saeid Sadri ◽  
Ali Yousefi
Keyword(s):  
State Space ◽  
Point Process ◽  
Goodness Of Fit ◽  
Estimation Accuracy ◽  
Model Parameters ◽  
Synaptic Connections ◽  
Synaptic Coupling ◽  
Modeling Framework ◽  
Space Modeling ◽  
Spiking Activity

It is of great interest to characterize the spiking activity of individual neurons in a cell ensemble. Many different mechanisms, such as synaptic coupling and the spiking activity of itself and its neighbors, drive a cell's firing properties. Though this is a widely studied modeling problem, there is still room to develop modeling solutions by simplifications embedded in previous models. The first shortcut is that synaptic coupling mechanisms in previous models do not replicate the complex dynamics of the synaptic response. The second is that the number of synaptic connections in these models is an order of magnitude smaller than in an actual neuron. In this research, we push this barrier by incorporating a more accurate model of the synapse and propose a system identification solution that can scale to a network incorporating hundreds of synaptic connections. Although a neuron has hundreds of synaptic connections, only a subset of these connections significantly contributes to its spiking activity. As a result, we assume the synaptic connections are sparse, and to characterize these dynamics, we propose a Bayesian point-process state-space model that lets us incorporate the sparsity of synaptic connections within the regularization technique into our framework. We develop an extended expectation-maximization. algorithm to estimate the free parameters of the proposed model and demonstrate the application of this methodology to the problem of estimating the parameters of many dynamic synaptic connections. We then go through a simulation example consisting of the dynamic synapses across a range of parameter values and show that the model parameters can be estimated using our method. We also show the application of the proposed algorithm in the intracellular data that contains 96 presynaptic connections and assess the estimation accuracy of our method using a combination of goodness-of-fit measures.

Pay no attention to that man behind the curtain

2016 ◽  
Vol 11 (3) ◽  
pp. 350-374 ◽  
Author(s):  
Chris Westbury
Keyword(s):  
Associative Learning ◽  
State Space ◽  
Neural Activity ◽  
Scientific Explanation ◽  
Word Meaning ◽  
Mental Simulation ◽  
High Dimensional ◽  
Weighted Constraints ◽  
Dimensional State Space ◽  
Semantic Domains

There is a distinction in scientific explanation between the explanandum, statements describing the empirical phenomenon to be explained, and the explanans, statements describing the evidence that allow one to predict that phenomenon. To avoid tautology, these sets of statements must refer to distinct domains. A scientific explanation of semantics must be grounded in explanans that appeal to entities from non-semantic domains. I consider as examples eight candidate domains (including affect, lexical or sub-word co-occurrence, mental simulation, and associative learning) that could ground semantics. Following Wittgenstein (1954), I propose adjudicating between these different domains is difficult because of the reification of a word’s ‘meaning’ as an atomistic unit. If we abandon the idea of the meaning of a word as being an atomistic unit and instead think of word meaning as a set of dynamic and disparate embodied states unified by a shared label, many apparent problems associated with identifying a meaning’s ‘true’ explanans disappear. Semantics can be considered as sets of weighted constraints that are individually sufficient for specifying and labeling a subjectively-recognizable location in the high dimensional state space defined by our neural activity.

scholarly journals State-space models reveal bursty movement behaviour of dance event visitors

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Philip Rutten ◽  
Michael H. Lees ◽  
Sander Klous ◽  
Peter M. A. Sloot
Keyword(s):  
State Space ◽  
Waiting Times ◽  
Movement Ecology ◽  
Joint Estimation ◽  
Movement Behaviour ◽  
Modeling Framework ◽  
Movement Data ◽  
Space Modeling ◽  
Crowd Behaviour ◽  
Heavy Tailed

AbstractPedestrian movements during large crowded events naturally consist of different modes of movement behaviour. Despite its importance for understanding crowd dynamics, intermittent movement behaviour is an aspect missing in the existing crowd behaviour literature. Here we analyse movement data generated from nearly 600 Wi-Fi sensors during large entertainment events in the Johan Cruijff ArenA football stadium in Amsterdam. We use the state-space modeling framework to investigate intermittent motion patterns. Movement models from the field of movement ecology are used to analyse individual pedestrian movement. Joint estimation of multiple movement tracks allows us to investigate statistical properties of measured movement metrics. We show that behavioural switching is not independent of external events, and the probability of being in one of the behavioural states changes over time. In addition, we show that the distribution of waiting times deviates from the exponential and is best fit by a heavy-tailed distribution. The heavy-tailed waiting times are indicative of bursty movement dynamics, which are here for the first time shown to characterise pedestrian movements in dense crowds. Bursty crowd behaviour has important implications for various diffusion-related processes, such as the spreading of infectious diseases.

scholarly journals Capturing human categorization of natural images by combining deep networks and cognitive models

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Ruairidh M. Battleday ◽  
Joshua C. Peterson ◽  
Thomas L. Griffiths
Keyword(s):  
Cognitive Modeling ◽  
Model Development ◽  
Cognitive Models ◽  
Natural Images ◽  
High Dimensional ◽  
Object Categories ◽  
Image Representations ◽  
Low Dimensional ◽  
Natural Settings ◽  
Human Categorization

Abstract Human categorization is one of the most important and successful targets of cognitive modeling, with decades of model development and assessment using simple, low-dimensional artificial stimuli. However, it remains unclear how these findings relate to categorization in more natural settings, involving complex, high-dimensional stimuli. Here, we take a step towards addressing this question by modeling human categorization over a large behavioral dataset, comprising more than 500,000 judgments over 10,000 natural images from ten object categories. We apply a range of machine learning methods to generate candidate representations for these images, and show that combining rich image representations with flexible cognitive models captures human decisions best. We also find that in the high-dimensional representational spaces these methods generate, simple prototype models can perform comparably to the more complex memory-based exemplar models dominant in laboratory settings.

Decoding Hidden Cognitive States From Behavior and Physiology Using a Bayesian Approach

2019 ◽  
Vol 31 (9) ◽  
pp. 1751-1788 ◽  
Author(s):  
Ali Yousefi ◽  
Ishita Basu ◽  
Angelique C. Paulk ◽  
Noam Peled ◽  
Emad N. Eskandar ◽  
...  
Keyword(s):  
Cognitive Processes ◽  
Goodness Of Fit ◽  
Spectral Power ◽  
Field Potential ◽  
High Dimensional ◽  
Cognitive State ◽  
Modeling Framework ◽  
Neural Data ◽  
Space Modeling ◽  
The Relationship

Cognitive processes, such as learning and cognitive flexibility, are both difficult to measure and to sample continuously using objective tools because cognitive processes arise from distributed, high-dimensional neural activity. For both research and clinical applications, that dimensionality must be reduced. To reduce dimensionality and measure underlying cognitive processes, we propose a modeling framework in which a cognitive process is defined as a low-dimensional dynamical latent variable—called a cognitive state, which links high-dimensional neural recordings and multidimensional behavioral readouts. This framework allows us to decompose the hard problem of modeling the relationship between neural and behavioral data into separable encoding-decoding approaches. We first use a state-space modeling framework, the behavioral decoder, to articulate the relationship between an objective behavioral readout (e.g., response times) and cognitive state. The second step, the neural encoder, involves using a generalized linear model (GLM) to identify the relationship between the cognitive state and neural signals, such as local field potential (LFP). We then use the neural encoder model and a Bayesian filter to estimate cognitive state using neural data (LFP power) to generate the neural decoder. We provide goodness-of-fit analysis and model selection criteria in support of the encoding-decoding result. We apply this framework to estimate an underlying cognitive state from neural data in human participants ([Formula: see text]) performing a cognitive conflict task. We successfully estimated the cognitive state within the 95% confidence intervals of that estimated using behavior readout for an average of 90% of task trials across participants. In contrast to previous encoder-decoder models, our proposed modeling framework incorporates LFP spectral power to encode and decode a cognitive state. The framework allowed us to capture the temporal evolution of the underlying cognitive processes, which could be key to the development of closed-loop experiments and treatments.

A Framework for Control Oriented Modeling of PEM Fuel Cells

2015 ◽  
Author(s):  
Benjamin L. Pence ◽  
Jixin Chen
Keyword(s):  
Fuel Cells ◽  
State Space ◽  
Polymer Electrolyte Membrane ◽  
Pem Fuel Cells ◽  
Algebraic Equations ◽  
Transient Effects ◽  
Modeling Framework ◽  
Two Phase ◽  
One Dimensional ◽  
Space Modeling

This paper develops a framework for along-the-channel and through-the-membrane control oriented modeling of polymer electrolyte membrane (PEM) fuel cells. The initial modeling framework is spatially one-dimensional by one-dimensional (1+1D) and is described by unsteady partial differential equations (PDEs). Numerical techniques convert the PDEs and boundary conditions to ordinary differential and algebraic equations that are convenient for state-space modeling. The modeling framework includes two-phase, thermal, and other transient effects. The generality of the modeling framework and its ability to be represented in state-space form facilitate complexity reduction and control-oriented application.

Sign in / Sign up

Export Citation Format

Share Document