Symmetry-Based Representations for Artificial and Biological General Intelligence

by   Irina Higgins, et al.

Biological intelligence is remarkable in its ability to produce complex behaviour in many diverse situations through data efficient, generalisable and transferable skill acquisition. It is believed that learning "good" sensory representations is important for enabling this, however there is little agreement as to what a good representation should look like. In this review article we are going to argue that symmetry transformations are a fundamental principle that can guide our search for what makes a good representation. The idea that there exist transformations (symmetries) that affect some aspects of the system but not others, and their relationship to conserved quantities has become central in modern physics, resulting in a more unified theoretical framework and even ability to predict the existence of new particles. Recently, symmetries have started to gain prominence in machine learning too, resulting in more data efficient and generalisable algorithms that can mimic some of the complex behaviours produced by biological intelligence. Finally, first demonstrations of the importance of symmetry transformations for representation learning in the brain are starting to arise in neuroscience. Taken together, the overwhelming positive effect that symmetries bring to these disciplines suggest that they may be an important general framework that determines the structure of the universe, constrains the nature of natural tasks and consequently shapes both biological and artificial intelligence.


page 1

page 4

page 6

page 10

page 12

page 14


Questions to Guide the Future of Artificial Intelligence Research

The field of machine learning has focused, primarily, on discretized sub...

Meta-learning in natural and artificial intelligence

Meta-learning, or learning to learn, has gained renewed interest in rece...

The relationship between Biological and Artificial Intelligence

Intelligence can be defined as a predominantly human ability to accompli...

Towards a Definition of Disentangled Representations

How can intelligent agents solve a diverse set of tasks in a data-effici...

Space as an invention of biological organisms

The question of the nature of space around us has occupied thinkers sinc...

The passive symmetries of machine learning

Any representation of data involves arbitrary investigator choices. Beca...

Nonlinearities in Steerable SO(2)-Equivariant CNNs

Invariance under symmetry is an important problem in machine learning. O...

Please sign up or login with your details

Forgot password? Click here to reset