Deep Active Learning


About This Project

Active learning is a supervised learning framework in which rather than building a model that iterates through a labelled dataset, the model is given unlabelled data and chooses on its own which data points would be most valuable if labelled. Obtaining unlabelled data is significantly easier than obtaining labelled data, and moreover a strong active learning model would be much more efficient at learning if it were proficient in choosing optimal data points query for labels, so the project has significant practical applications.

Project Members

Deep Active Learning

currently no documents uploaded for this project

<< Back to Portfolio