Skip to main content

What is disentangling and does intelligence need it?

Irina Higgins ( Google DeepMind )

Despite the advances in modern deep learning approaches, we are still quite far from the generality, robustness and data efficiency of biological intelligence. In this talk I will suggest that this gap may be narrowed by re-focusing from implicit representation learning prevalent in end-to-end deep learning approaches to explicit unsupervised representation learning. In particular, I will discuss the value of disentangled visual representations acquired in an unsupervised manner loosely inspired by biological intelligence. In particular, this talk will connect disentangling with the ideas of symmetry transformations from physics to make a claim that disentangled representations reflect important world structure. I will then go over a few first demonstrations of how such representations can be useful in practice for continual learning, acquiring reinforcement learning (RL) policies that are more robust to transfer scenarios that standard RL approaches, and building abstract compositional visual concepts which make possible imagination of meaningful and diverse samples beyond the training data distribution.

Speaker bio

Irina is a research scientist at DeepMind, where she works in the Froniers team. Her work aims to bring together insights from the fields of neuroscience and physics to advance general artificial intelligence through improved representation learning. Before joining DeepMind, Irina was a British Psychological Society Undergraduate Award winner for her achievements as an undergraduate student in Experimental Psychology at Westminster University, followed by a DPhil at the Oxford Centre for Computational Neuroscience and Artificial Intelligence, where she focused on understanding the computational principles underlying speech processing in the auditory brain. During her DPhil, Irina also worked on developing poker AI, applying machine learning in the finance sector, and working on speech recognition at Google Research.

 

 

Share this: