Back to search

École de technologie supérieure

The mechanics of CNN filtering with rectification

Abstract

dc:description

This thesis is the first investigation of the mechanical properties of convolutional filtering with rectification through the lens of symmetric and antisymmetric convolutional kernels. Symmetric kernels cause image content to diffuse isotropically with no net displacement, whereas antisymmetric kernels cause directional displacement and attenuation effects when sequentially convolved at varying orientations. The speed of information displacement is linearly related to the ratio of antisymmetric vs total kernel energy. Symmetry properties are analyzed in the spectral domain via the discrete cosine transform (DCT), where the structure of small convolutional filters (e.g. 3 × 3 pixels) is dominated by low-frequency bases, specifically the DC Σ and gradient components ∇, which define the fundamental modes of information propagation. Applying this analysis to trained CNN filters, we find that low-order frequency components (specifically DC and gradient bases) dominate, accounting for over 92% of classification performance in popular models such as VGG16 and ResNet50. The symmetry of kernels evolves with depth: early layers are predominantly antisymmetric, emphasizing oriented gradients, whereas deeper layers become increasingly symmetric, promoting diffusion. Furthermore, we observe that filters organize into correlated bipolar orientation structures across channels and layers, maintaining directional alignment between consecutive kernels while suppressing orthogonal activations. This work provides a systematic framework for analyzing, interpreting, and potentially guiding the design of improved architectures and learning algorithms through their geometric and spectral structure.

Degree

thesis:*
Name thesis:degree_name
Mémoire de maîtrise électronique
Level thesis:degree_level
masters
Grantor dc:publisher
École de technologie supérieure
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Frija-Altarac, Liam

Subjects

dc:subject × 1

Rights

Language dc:language
en

Identifiers

dc:identifier.*
Identifier
INSERT-YOUR-LIBRARY-ID-HERE3835

Chain of custody

source
Harvested from
ETS (Quebec)
Base URL
espace.etsmtl.ca/cgi/oai2
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Frija-Altarac, Liam. The mechanics of CNN filtering with rectification. masters thesis, École de technologie supérieure, 2025.