
0.25
0.5
0.75
1.25
1.5
1.75
2
System Identification of Enzymatic Control Processes Using Population Monte Carlo Methods
Published on 2007-04-046962 Views
We demonstrate the superiority of Population Monte Carlo techniques over standard Metropolis Markov Chain Monte Carlo (MCMC) methods for inferring optimal parameters for a particular mechanistic model
Related categories
Presentation
System Identification of Enzymatic Control Processes Using Population Monte Carlo Methods00:01
Outline00:35
Biological Motivation01:49
Circadian Rhythms02:45
A Minimal Model to Describe Circadian Control03:48
An Extended Goodwin Model04:49
Example of Possible Outputs05:56
Long Term Goals06:10
Bayesian Model Inference07:07
Model Inference07:17
Defining the Model and the Data08:04
Defining a Likelihood Function08:41
A Standard MCMC Approach09:17
A Random Walk in Parameter Space09:33
Engineering a Solution10:12
Implementation10:58
Results - 15 Parallel Chains12:45
Results - 30 Parallel Chains13:25
A Population Monte Carlo Approach14:06
Comparison of Population Monte Carlo14:31
How Non-Markovian Population Monte Carlo Works15:43
Features of Non-Markovian Population Monte Carlo16:50
Results for a Population of 40 Particles17:08
Potential Pitfalls17:28
Summary of Non-Markovian Population Monte Ca18:05