Machine learning and cognitive competence

The speed and accuracy with which we process and evaluate information is a measure of cognitive competence. Parametric measures of mental-attentional capacity assess cognitive competence using multiple levels of complexity.  Individual differences on cognitive competence are evident within groups and across age.  Research shows that mental attentional capacity improves gradually over and this growth corresponds to brain-related indices.  Ultrasonography is an unusual method for evaluating hemodynamic responses in healthy individuals, yet it is portable and comparatively inexpensive.  We build prediction models of solving classification and regression based on Logistic Regression, Lasso Regression, Ridge Regression and Support Vector Machine Classifier, Random Forest Classifier, Logistic Regression Classifier.  We presented preliminary results and discussed the output in context of machine learning approaches and practical applications in educational settings. 

Visiting Speakers: Ekaterina Kondrateva¹ , Nikolay Skuratov^1,2 ,  Maxim Sharaev, PhD
¹Skolkovo Institute of Science and Technology and ²Moscow Institute of Physics and Technology