Andrew Glassner joins fxguide’s Mike Seymour to discuss machine learning and its role in visual effects. Without a doubt, Deep Learning is one of the hottest topics in VFX and one that is opening up a world of new tools. In our continuing ‘conversations’ fxpodcasts, we chat about the various techniques that are shaping VFX.
Dr. Andrew Glassner is a research scientist specializing in computer graphics and deep learning. He is currently a Senior Research Scientist at Weta Digital, where he works on integrating deep learning with the production of world-class visual effects for films and television. He has previously worked as a researcher at labs such as the IBM Watson Lab, Xerox PARC, and Microsoft Research. He was Editor in Chief of ACM TOG, the premier research journal in graphics, and Technical Papers Chair for SIGGRAPH, the premier conference in graphics. He’s written or edited a dozen technical books on computer graphics, his newest book is Deep Learning: A Visual Approach.
The book is a highly accessible, richly illustrated introduction to deep learning that offers visual and conceptual explanations instead of equations. As a reader, you see how to use key deep learning algorithms without the need for complex math. This book builds on Andrew’s ‘sold-out’ master classes at conferences such as SIGGRAPH and FMX. The book provides an artist with an introduction to deep learning and how to use key deep learning algorithms & concepts such as
- Machine Learning Classification
- Neural Networks and CNN and Backpropagation
- Recurrent Nural Networks (RNN)
- Reinforcement Learning and
- Generative Adversarial Networks (GANs) including Neural Style Transfers
The New York Times wrote, “Andrew Glassner [is one] of the most respected talents in the world of computer graphics research.” This book is the perfect bridge to understanding the rapidly evolving world of AI in VFX. The style is accessible, friendly and open, as you will hear is Andrew Glassner in the discussion in this episode of the fxpodcast.