Image creation using Generative Adversarial Networks (GANs)
This workshop will guide you through the process of training a Generative Adversarial Network (GAN) to generate image contents in DIGITS. You will learn how to: Use Generative Adversarial Networks (GANs) to create handwritten numbers; Visualize the feature space and use attribute vector to generate image analogies; Train a GAN to generate images with set attributes. Upon completion of this workshop, you will be able to use GANs to generate images by manipulating feature space.
David Nola is a Deep Learning Solutions Architect at NVIDIA specializing in computer vision workflows and time series problems. He works with professionals in Healthcare, the Industrial Internet of Things, and Financial Services to GPU accelerate their Data Science processes and provide education and proof of concepts for deep learning projects. He got his Master's degree from UCLA in Computer Science where he specialized in Artificial Intelligence, Deep Learning, and Hyperparameter Optimization.