The ISC is part of the Johns Hopkins Applied Physics Laboratory and will follow all current policies. Please visit the JHU/APL page for more information on the Lab's visitor guidance.

2017

Feature Selection Methods for Zero-Shot Learning of Neural Activity


Abstract

Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows) have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy.

Citation

article: Caceres_2017 doi: 10.3389/fninf.2017.00041 url: https://doi.org/10.3389/fninf.2017.00041 year: 2017 month: jun publisher: Frontiers Media SA volume: 11 author: Caceres Carlos A. and Roos Matthew J. and Rupp Kyle M. and Milsap Griffin and Crone Nathan E. and Wolmetz Michael E. and Ratto Christopher R. title: Feature Selection Methods for Zero-Shot Learning of Neural Activity journal: Frontiers in Neuroinformatics

Citation

article: Caceres_2017 doi: 10.3389/fninf.2017.00041 url: https://doi.org/10.3389/fninf.2017.00041 year: 2017 month: jun publisher: Frontiers Media SA volume: 11 author: Caceres Carlos A. and Roos Matthew J. and Rupp Kyle M. and Milsap Griffin and Crone Nathan E. and Wolmetz Michael E. and Ratto Christopher R. title: Feature Selection Methods for Zero-Shot Learning of Neural Activity journal: Frontiers in Neuroinformatics