Dr S. M. Ali Eslami (Research Scientist, Google DeepMind)
Unsupervised Doodling and Painting with Generative Agents
The computational techniques that drive the field of machine learning are increasingly being used for creative endeavours. In particular, recent advances in generative modelling provide a tantalising glimpse of how machine learning may one day find a place in the modern artist’s tool set. In this talk I will investigate using reinforcement learning agents as generative models of images. A generative agent controls a simulated painting environment, and is trained with rewards provided by a discriminator network simultaneously trained to assess the realism of the agent’s samples. We find that when sufficiently constrained, generative agents can learn to produce images with a degree of visual abstraction, despite having only ever seen real photographs and no trajectories. And given enough time with the painting environment, they can produce images with considerable realism. These results show that, under the right circumstances, some aspects of human drawing can emerge from simulated embodiment, without the need for external supervision, imitation or social cues.
—
Machine learning offers a new and universal way of looking at the world, which is radically different than traditional domain-focused and theory-based approaches. However, while new machine learning algorithms such as deep learning have created a wave of applications in computer vision and natural language translation, there are a lot of complex applications which are yet to be investigated.
In recent years there have been significant advances in reinforcement learning, generative models and topological data analysis for media creation, design exploration, and urban analytics.
About the event:
This talk will focus on the domain of machine learning for creativity and design, looking at the applications of unsupervised learning in the context of urban system modelling, structural design explorations, and the use of reinforcement learning in generative arts which provides a glimpse of how machine learning may one day find its place in the toolset of artists and designers.
Add comment