Shinsuke Koyama
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shinsuke Koyama has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Robert E. Kass
Machine Learning Department, Carnegie Mellon University
5 shared publications - Cosma Rohilla Shalizi
Statistics Department, Carnegie Mellon University, Pittsburgh, USA
2 shared publications - Lucia Castellanos Pérez-Bolde
Graduate Student Machine Learning Department and Center Neural Basis of Cognition Carnegie Mellon University 15213 Pittsburgh PA
2 shared publications - Andrew B. Schwartz
University of Pittsburgh
1 shared publication - Andrew S. Whitford
Department of Bioengineering, Center for the Neural Basis of Cognition, University of Pittsburgh, Pittsburgh, PA, USA
1 shared publication - Emery N. Brown
Member, IEEE, Neuroscience Statistics Research Laboratory, Department of Anesthesia and Critical Care, Massachusetts General Hospital, Boston, MA 02114, U.S.A.; Department of Brain and Cognitive Sciences. MIT/Harvard Medical School Division of Health Sciences and Technology, Cambridge, MA 02139, U.S.A.
1 shared publication
Latest Publications
- Open Access
Approximate Methods for State-Space Models
State-space models provide an important body of techniques for analyzing time-series, but their use requires estimating unobserved states. The optimal estimate of the state is its conditional expectation given the observation histories, and computing this expectation is hard when there are nonlinearities. Existing filtering methods, including sequential Monte Carlo, tend to be either inaccurate or slow. In this paper, we study a nonlinear filter for nonlinear/non-Gaussian state-space models, which uses Laplace's method, an asymptotic series expansion, to approximate the state's conditional mean and variance, together with a Gaussian conditional distribution. This {\em Laplace-Gaussian filter} (LGF) gives fast, recursive, deterministic state estimates, with an error which is set by the stochastic characteristics of the model and is, we show, stable over time. We illustrate the estimation ability of the LGF by applying it to the problem of neural decoding and compare it to sequential Monte Carlo both in simulations and with real data. We find that the LGF can deliver superior results in a small fraction of the computing time.
Open AccessApproximate Methods for State-Space Models
State-space models provide an important body of techniques for analyzing time-series, but their use requires estimating unobserved states. The optimal estimate of the state is its conditional expectation given the observation histories, and computing this expectation is hard when there are nonlinearities. Existing filtering methods, including sequential Monte Carlo, tend to be either inaccurate or slow. In this paper, we study a nonlinear filter for nonlinear/non-Gaussian state-space models, which uses Laplace's method, an asymptotic series expansion, to approximate the state's conditional mean and variance, together with a Gaussian conditional distribution. This {\em Laplace-Gaussian filter} (LGF) gives fast, recursive, deterministic state estimates, with an error which is set by the stochastic characteristics of the model and is, we show, stable over time. We illustrate the estimation ability of the LGF by applying it to the problem of neural decoding and compare it to sequential Monte Carlo both in simulations and with real data. We find that the LGF can deliver superior results in a small fraction of the computing time.
- 1 March 2010
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 105 (489) , 170-180
Approximate Methods for State-Space Models
State-space models provide an important body of techniques for analyzing time series, but their use requires estimating unobserved states. The optimal estimate of the state is its conditional expec...
- 1 March 2010
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 105 (489) , 170-180
Approximate Methods for State-Space Models
State-space models provide an important body of techniques for analyzing time series, but their use requires estimating unobserved states. The optimal estimate of the state is its conditional expec...
- 11 November 2009
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 29 (1-2) , 73-87
Comparison of brain–computer interface decoding algorithms in open-loop and closed-loop control
Neuroprosthetic devices such as a computer cursor can be controlled by the activity of cortical neurons when an appropriate algorithm is used to decode motor intention. Algorithms which have been proposed for this purpose range from the simple population vector algorithm (PVA) and optimal linear estimator (OLE) to various versions of Bayesian decoders. Although Bayesian decoders typically provide the most accurate off-line reconstructions, it is not known which model assumptions in these algorithms are critical for improving decoding performance. Furthermore, it is not necessarily true that improvements (or deficits) in off-line reconstruction will translate into improvements (or deficits) in on-line control, as the subject might compensate for the specifics of the decoder in use at the time. Here we show that by comparing the performance of nine decoders, assumptions about uniformly distributed preferred directions and the way the cursor trajectories are smoothed have the most impact on decoder performance in off-line reconstruction, while assumptions about tuning curve linearity and spike count variance play relatively minor roles. In on-line control, subjects compensate for directional biases caused by non-uniformly distributed preferred directions, leaving cursor smoothing differences as the largest single algorithmic difference driving decoder performance.
- 11 November 2009
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 29 (1-2) , 73-87
Comparison of brain–computer interface decoding algorithms in open-loop and closed-loop control
Neuroprosthetic devices such as a computer cursor can be controlled by the activity of cortical neurons when an appropriate algorithm is used to decode motor intention. Algorithms which have been proposed for this purpose range from the simple population vector algorithm (PVA) and optimal linear estimator (OLE) to various versions of Bayesian decoders. Although Bayesian decoders typically provide the most accurate off-line reconstructions, it is not known which model assumptions in these algorithms are critical for improving decoding performance. Furthermore, it is not necessarily true that improvements (or deficits) in off-line reconstruction will translate into improvements (or deficits) in on-line control, as the subject might compensate for the specifics of the decoder in use at the time. Here we show that by comparing the performance of nine decoders, assumptions about uniformly distributed preferred directions and the way the cursor trajectories are smoothed have the most impact on decoder performance in off-line reconstruction, while assumptions about tuning curve linearity and spike count variance play relatively minor roles. In on-line control, subjects compensate for directional biases caused by non-uniformly distributed preferred directions, leaving cursor smoothing differences as the largest single algorithmic difference driving decoder performance.
- 21 October 2009
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 29 (1-2) , 183-191
A characterization of the time-rescaled gamma process as a model for spike trains
The occurrence of neuronal spikes may be characterized by not only the rate but also the irregularity of firing. We have recently developed a Bayes method for characterizing a sequence of spikes in terms of instantaneous rate and irregularity, assuming that interspike intervals (ISIs) are drawn from a distribution whose shape may vary in time. Though any parameterized family of ISI distribution can be installed in the Bayes method, the ability to detect firing characteristics may depend on the choice of a family of distribution. Here, we select a set of ISI metrics that may effectively characterize spike patterns and determine the distribution that may extract these characteristics. The set of the mean ISI and the mean log ISI are uniquely selected based on the statistical orthogonality, and accordingly the corresponding distribution is the gamma distribution. By applying the Bayes method equipped with the gamma distribution to spike sequences derived from different ISI distributions such as the log-normal and inverse-Gaussian distribution, we confirm that the gamma distribution effectively extracts the rate and the shape factor.
- 21 October 2009
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 29 (1-2) , 183-191
A characterization of the time-rescaled gamma process as a model for spike trains
The occurrence of neuronal spikes may be characterized by not only the rate but also the irregularity of firing. We have recently developed a Bayes method for characterizing a sequence of spikes in terms of instantaneous rate and irregularity, assuming that interspike intervals (ISIs) are drawn from a distribution whose shape may vary in time. Though any parameterized family of ISI distribution can be installed in the Bayes method, the ability to detect firing characteristics may depend on the choice of a family of distribution. Here, we select a set of ISI metrics that may effectively characterize spike patterns and determine the distribution that may extract these characteristics. The set of the mean ISI and the mean log ISI are uniquely selected based on the statistical orthogonality, and accordingly the corresponding distribution is the gamma distribution. By applying the Bayes method equipped with the gamma distribution to spike sequences derived from different ISI distributions such as the log-normal and inverse-Gaussian distribution, we confirm that the gamma distribution effectively extracts the rate and the shape factor.
- 30 July 2009
- Published by Springer Nature in Annals of the Institute of Statistical Mathematics
- Vol. 62 (1) , 37-59
Bayesian decoding of neural spike trains
- 30 July 2009
- Published by Springer Nature in Annals of the Institute of Statistical Mathematics
- Vol. 62 (1) , 37-59
Bayesian decoding of neural spike trains
- 28 April 2009
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 29 (1-2) , 89-105
Efficient computation of the maximum a posteriori path and parameter estimation in integrate-and-fire and more general state-space models
A number of important data analysis problems in neuroscience can be solved using state-space models. In this article, we describe fast methods for computing the exact maximum a posteriori (MAP) path of the hidden state variable in these models, given spike train observations. If the state transition density is log-concave and the observation model satisfies certain standard assumptions, then the optimization problem is strictly concave and can be solved rapidly with Newton–Raphson methods, because the Hessian of the loglikelihood is block tridiagonal. We can further exploit this block-tridiagonal structure to develop efficient parameter estimation methods for these models. We describe applications of this approach to neural decoding problems, with a focus on the classic integrate-and-fire model as a key example.
- 28 April 2009
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 29 (1-2) , 89-105
Efficient computation of the maximum a posteriori path and parameter estimation in integrate-and-fire and more general state-space models
A number of important data analysis problems in neuroscience can be solved using state-space models. In this article, we describe fast methods for computing the exact maximum a posteriori (MAP) path of the hidden state variable in these models, given spike train observations. If the state transition density is log-concave and the observation model satisfies certain standard assumptions, then the optimization problem is strictly concave and can be solved rapidly with Newton–Raphson methods, because the Hessian of the loglikelihood is block tridiagonal. We can further exploit this block-tridiagonal structure to develop efficient parameter estimation methods for these models. We describe applications of this approach to neural decoding problems, with a focus on the classic integrate-and-fire model as a key example.
- Open Access
- 1 July 2008
- Published by MIT Press in Neural Computation
- Vol. 20 (7) , 1776-1795
Spike Train Probability Models for Stimulus-Driven Leaky Integrate-and-Fire Neurons
Mathematical models of neurons are widely used to improve understanding of neuronal spiking behavior. These models can produce artificial spike trains that resemble actual spike train data in important ways, but they are not very easy to apply to the analysis of spike train data. Instead, statistical methods based on point process models of spike trains provide a wide range of data-analytical techniques. Two simplified point process models have been introduced in the literature: the time-rescaled renewal process (TRRP) and the multiplicative inhomogeneous Markov interval (m-IMI) model. In this letter we investigate the extent to which the TRRP and m-IMI models are able to fit spike trains produced by stimulus-driven leaky integrate-and-fire (LIF) neurons. With a constant stimulus, the LIF spike train is a renewal process, and the m-IMI and TRRP models will describe accurately the LIF spike train variability. With a time-varying stimulus, the probability of spiking under all three of these models depends on both the experimental clock time relative to the stimulus and the time since the previous spike, but it does so differently for the LIF, m-IMI, and TRRP models. We assessed the distance between the LIF model and each of the two empirical models in the presence of a time-varying stimulus. We found that while lack of fit of a Poisson model to LIF spike train data can be evident even in small samples, the m-IMI and TRRP models tend to fit well, and much larger samples are required before there is statistical evidence of lack of fit of the m-IMI or TRRP models. We also found that when the mean of the stimulus varies across time, the m-IMI model provides a better fit to the LIF data than the TRRP, and when the variance of the stimulus varies across time, the TRRP provides the better fit.
- 1 July 2008
- Published by MIT Press in Neural Computation
- Vol. 20 (7) , 1776-1795
Open AccessSpike Train Probability Models for Stimulus-Driven Leaky Integrate-and-Fire Neurons
Mathematical models of neurons are widely used to improve understanding of neuronal spiking behavior. These models can produce artificial spike trains that resemble actual spike train data in important ways, but they are not very easy to apply to the analysis of spike train data. Instead, statistical methods based on point process models of spike trains provide a wide range of data-analytical techniques. Two simplified point process models have been introduced in the literature: the time-rescaled renewal process (TRRP) and the multiplicative inhomogeneous Markov interval (m-IMI) model. In this letter we investigate the extent to which the TRRP and m-IMI models are able to fit spike trains produced by stimulus-driven leaky integrate-and-fire (LIF) neurons. With a constant stimulus, the LIF spike train is a renewal process, and the m-IMI and TRRP models will describe accurately the LIF spike train variability. With a time-varying stimulus, the probability of spiking under all three of these models depends on both the experimental clock time relative to the stimulus and the time since the previous spike, but it does so differently for the LIF, m-IMI, and TRRP models. We assessed the distance between the LIF model and each of the two empirical models in the presence of a time-varying stimulus. We found that while lack of fit of a Poisson model to LIF spike train data can be evident even in small samples, the m-IMI and TRRP models tend to fit well, and much larger samples are required before there is statistical evidence of lack of fit of the m-IMI or TRRP models. We also found that when the mean of the stimulus varies across time, the m-IMI model provides a better fit to the LIF data than the TRRP, and when the variance of the stimulus varies across time, the TRRP provides the better fit.