Creating Deep Convolutional Neural Networks for Image Classification
Masterclass Description
Convolutional neural networks (CNN) are used by researchers in a wide variety of fields for computer vision tasks, such as image classification, object detection, and boundary segmentation. In this workshop, we will explore the architecture underpinning CNNs to understand how they allow machines “to see” data and what this means for scholars in the humanities. Attendees will gain hands-on experience training a CNN through Google’s Teachable Machine, a web-based platform designed to introduce machine learning in an accessible and user-friendly manner without code. Through a series of guided exercises, participants will learn the process of uploading a dataset, monitoring the training of the model, and evaluating performance. Particular emphasis will be placed on recognizing the potential biases of datasets and the importance of accurate classification when utilizing machine learning algorithms.
Speaker Biography
Nabeel Siddiqui is the Director for the Center for Teaching and Learning at Susquehanna University, where he also serves as an Assistant Professor of Digital Media. His research focuses on the digital humanities, computer vision, the history of technology, online culture, and data science. Currently, he is completing a manuscript entitled Cultural Analytics in R: A Tidy Approach, which explores how computational analysis and statuses can assist in enriching our understanding of culture, especially in situations where qualitative research may be difficult or misleading.
Booking Information
Upon booking, attendees will receive an automated confirmation email. This event will take place on Zoom. Attendees will receive a second email closer to the event date which will provide the Zoom link. Please use the same email for registering and when logging into Zoom.
Please inform us of any access requirements by emailing cdcs@ed.ac.uk. Further details about how CDCS uses your information obtained from booking onto our events can be found in our Events Privacy Statement.
