On Invariance and Selectivity in Representation Learning

Abstract

We discuss data representation which can be learned automatically from data, are invariant to transformations, and at the same time selective, in the sense that two points have the same representation only if they are one the transformation of the other. The mathematical results here sharpen some of the key claims of i-theory -- a recent theory of feedforward processing in sensory cortex.

References in corpus (1)

• Unsupervised Learning of Invariant Representations in Hierarchical Architectures

Cited by in corpus (7)

• Mathematics of Deep Learning
• A Probabilistic Theory of Deep Learning
• Visual Representations: Defining Properties and Deep Approximations
• Deep Convolutional Networks are Hierarchical Kernel Machines
• Visual-Inertial-Semantic Scene Representation for 3-D Object Detection
• Understanding the Generalization Benefit of Model Invariance from a Data Perspective
• Emergence of Selective Invariance in Hierarchical Feed Forward Networks