+DS vLE: Convolutional Neural Networks for Image Analysis

Sep 21

Tuesday, September 21, 2021 - 12:00pm to 1:00pm

Virtual

Add to calendar »

Presenter

Tim Dunn

The convolutional neural network (CNN) represents the current state-of-the-art for image and video analysis, and is increasingly used for analyzing time series and other data with spatial or sequential structure. This session will provide an intuitive introduction to the fundamentals of CNNs, with an emphasis on hierarchical feature extraction and the convolution operation itself. Model training and transfer learning will also be discussed. Please register at least 15 minutes prior to the start of the session to allow time for the system to generate a personalized e-mail with the access link. This session is part of the Duke+DataScience (+DS) program virtual learning experiences (vLEs). To learn more, please visit https://plus.datascience.duke.edu