In this talk, we introduce the fundamentals of deep learning for image understanding. We begin by explaining the basics of convolutional neural networks (CNNs), and showing how CNNs are used to perform image classification and object detection. We provide an overview of the recent evolution of CNN topologies for object detection. We also illustrate typical use cases for CNN-based image classification and object detection, and provide a roadmap for getting started with deep learning for image understanding.
Introduction to Deep Learning for Image Understanding
Session Speakers
-
Zoran Sevarac
Associate Professor, University of Belgrade / Deep Netts
Zoran Sevarac is a professor teaching software engineering and AI at the University of Belgrade, and an AI researcher. He is also a Java community thought leader, recognized as a Java Champion and Duke's Choice Award winner. He has been involved in several open-source projects (Neuroph, NetBeans) and is currently working in the expert group for the Java technology standard for visual recognition. His long-term goal is to make AI more approachable for software developers, through the development of AI development tools and open standards. His latest project, Deep Netts, brings these ideas to life.
