DeepAI AI Chat
Log In Sign Up

Stopping criteria for boosting automatic experimental design using real-time fMRI with Bayesian optimization

by   Romy Lorenz, et al.

Bayesian optimization has been proposed as a practical and efficient tool through which to tune parameters in many difficult settings. Recently, such techniques have been combined with real-time fMRI to propose a novel framework which turns on its head the conventional functional neuroimaging approach. This closed-loop method automatically designs the optimal experiment to evoke a desired target brain pattern. One of the challenges associated with extending such methods to real-time brain imaging is the need for adequate stopping criteria, an aspect of Bayesian optimization which has received limited attention. In light of high scanning costs and limited attentional capacities of subjects an accurate and reliable stopping criteria is essential. In order to address this issue we propose and empirically study the performance of two stopping criteria.


page 1

page 2

page 3

page 4


Optimization, fast and slow: optimally switching between local and Bayesian optimization

We develop the first Bayesian Optimization algorithm, BLOSSOM, which sel...

Online Optimization of Stimulation Speed in an Auditory Brain-Computer Interface under Time Constraints

The decoding of brain signals recorded via, e.g., an electroencephalogra...

Stopping Criterion Design for Recursive Bayesian Classification: Analysis and Decision Geometry

Systems that are based on recursive Bayesian updates for classification ...

Active Bayesian Optimization: Minimizing Minimizer Entropy

The ultimate goal of optimization is to find the minimizer of a target f...

Enough is Enough: Towards Autonomous Uncertainty-driven Stopping Criteria

Autonomous robotic exploration has long attracted the attention of the r...

Modelling Stopping Criteria for Search Results using Poisson Processes

Text retrieval systems often return large sets of documents, particularl...

Design of Experiments for Verifying Biomolecular Networks

There is a growing trend in molecular and synthetic biology of using mec...