A SkillsCast for this session is not available.
https://github.com/deepmind/spiral
This paper proposes a very interesting application of RL on generating images. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, which creates a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets.
To mitigate these issues, SPIRAL is an adversarially trained agent that generates a program which is executed by a graphics engine to interpret and sample images. You can see it performing here: https://www.youtube.com/watch?v=iSyvwAwa7vk&feature=youtu.be
YOU MAY ALSO LIKE:
- Reinforcement Learning & Creative Applications (SkillsCast recorded in August 2019)
- Deep Learning Fundamentals with Leonardo De Marchi (Online Course on 3rd - 6th May 2021)
- Personal Engineering: Living Well at Work with Portia Tung (Online Meetup on 11th March 2021)
- Containers Beyond the Fundamentals, What Next? with Matt Saunders (Online Meetup on 18th March 2021)
- Building a Custom Type Provider (SkillsCast recorded in October 2020)
- Post Quantum Cryptography Apocalypse (SkillsCast recorded in September 2020)
Synthesizing Programs for Images using Reinforced Adversarial Learning
Ali Chaudhry
Ali is a self-taught programmer, currently doing a PhD in Artificial Intelligence and Education at University College London. His research focuses on applying human-centered learning science theories on Deep Reinforcement Learning algorithms. These days he's obsessed with GANs and Variational Autoencoders.