AI Essentials for Images and Video
Overview
AI can achieve state-of-the-art accuracy in many cognitive or perceptual tasks such as naming objects in a scene or recognizing optimal paths in an environment. But the AI workflow can be a challenging, as it involves preparing large data sets, creating a model (e.g., neural networks), and training, visualizing, and evaluating different models, using specialized hardware - often requiring unique programming knowledge.
In this seminar, we will demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. We will focus on a case study of computer vision in autonomous vehicles.
Highlights
- Simplifying the process of preparing and labelling image / video data
- Building and training deep neural networks for image tasks (e.g., classification, detection, segmentation)
- Deploying AI models to GPU through automated CUDA code generation
This event is part of a series of related topics. View the full list of events in this series.