DeepAI AI Chat
Log In Sign Up

Symmetry constrained machine learning

by   Doron L. Bergman, et al.

Symmetry, a central concept in understanding the laws of nature, has been used for centuries in physics, mathematics, and chemistry, to help make mathematical models tractable. Yet, despite its power, symmetry has not been used extensively in machine learning, until rather recently. In this article we show a general way to incorporate symmetries into machine learning models. We demonstrate this with a detailed analysis on a rather simple real world machine learning system - a neural network for classifying handwritten digits, lacking bias terms for every neuron. We demonstrate that ignoring symmetries can have dire over-fitting consequences, and that incorporating symmetry into the model reduces over-fitting, while at the same time reducing complexity, ultimately requiring less training data, and taking less time and resources to train.


Understanding Bias in Machine Learning

Bias is known to be an impediment to fair decisions in many domains such...

Testing for Geometric Invariance and Equivariance

Invariant and equivariant models incorporate the symmetry of an object t...

Cluster Algebras: Network Science and Machine Learning

Cluster algebras have recently become an important player in mathematics...

Symmetry Detection and Classification in Drawings of Graphs

Symmetry is a key feature observed in nature (from flowers and leaves, t...

Dimensionless machine learning: Imposing exact units equivariance

Units equivariance is the exact symmetry that follows from the requireme...

The passive symmetries of machine learning

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

Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't

The purpose of this article is to review the achievements made in the la...