Learning Spatially Structured Image Transformations Using Planar Neural Networks

TL;DR

This paper explores how planar neural networks can learn fundamental image transformations like translation, rotation, and scaling from perceptual data, analyzing factors affecting learning efficiency and transferability.

Contribution

It introduces a connectionist approach using planar neural networks to learn imagery transformations and examines how network design and data influence learning outcomes.

Findings

Network topology impacts learning efficiency.

Training data diversity affects transferability.

Shape variations influence transformation learning.

Abstract

Learning image transformations is essential to the idea of mental simulation as a method of cognitive inference. We take a connectionist modeling approach, using planar neural networks to learn fundamental imagery transformations, like translation, rotation, and scaling, from perceptual experiences in the form of image sequences. We investigate how variations in network topology, training data, and image shape, among other factors, affect the efficiency and effectiveness of learning visual imagery transformations, including effectiveness of transfer to operating on new types of data.