|
|
|
|
LEADER |
02088 am a22002533u 4500 |
001 |
61621 |
042 |
|
|
|a dc
|
100 |
1 |
0 |
|a Shimazaki, Hideaki
|e author
|
100 |
1 |
0 |
|a Harvard University-
|e contributor
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
|e contributor
|
100 |
1 |
0 |
|a Brown, Emery N.
|e contributor
|
100 |
1 |
0 |
|a Brown, Emery N.
|e contributor
|
700 |
1 |
0 |
|a Amari, Shun-ichi
|e author
|
700 |
1 |
0 |
|a Brown, Emery N.
|e author
|
700 |
1 |
0 |
|a Grun, Sonja
|e author
|
245 |
0 |
0 |
|a State-space analysis on time-varying correlations in parallel spike sequences
|
260 |
|
|
|b Institute of Electrical and Electronics Engineers,
|c 2011-03-07T22:09:50Z.
|
856 |
|
|
|z Get fulltext
|u http://hdl.handle.net/1721.1/61621
|
520 |
|
|
|a A state-space method for simultaneously estimating time-dependent rate and higher-order correlation underlying parallel spike sequences is proposed. Discretized parallel spike sequences are modeled by a conditionally independent multivariate Bernoulli process using a log-linear link function, which contains a state of higher-order interaction factors. A nonlinear recursive filtering formula is derived from a log-quadratic approximation to the posterior distribution of the state. Together with a fixed-interval smoothing algorithm, time-dependent log-linear parameters are estimated. The smoothed estimates are optimized via EM-algorithm such that their prior covariance matrix maximizes the expected complete data log-likelihood. In addition, we perform model selection on the hierarchical log-linear state-space models to avoid over-fitting. Application of the method to simultaneously recorded neuronal spike sequences is expected to contribute to uncover dynamic cooperative activities of neurons in relation to behavior.
|
520 |
|
|
|a National Institute of Mental Health (U.S.) (R01 MH59733)
|
520 |
|
|
|a National Institutes of Health (U.S.). Pioneer Award (DP1 OD 003646)
|
546 |
|
|
|a en_US
|
655 |
7 |
|
|a Article
|
773 |
|
|
|t IEEE International Conference on Acoustics, Speech, and Signal Processing : [proceedings] (ICASSP)
|