paper-with-me

Papers

Algebraic Representations for Faster Predictions in Convolutional Neural Networks

2024-08-14 · Johnny Joyce, Jan Verschelde

Convolutional neural networks (CNNs) are a popular choice of model for tasks in computer vision. When CNNs are made with many layers, resulting in a deep neural network, skip connections may be added to create an easier gradient optimization problem while retaining model expressiveness. In this paper, we show that arbitrarily complex, trained, linear CNNs with skip connections can be simplified into a single-layer model, resulting in greatly reduced computational requirements during prediction time. We also present a method for training nonlinear models with skip connections that are gradually removed throughout training, giving the benefits of skip connections without requiring computational overhead during during prediction time. These results are demonstrated with practical examples on Residual Networks (ResNet) architecture.

📄 PDF Abstract BibTeX arXiv:2408.07815

Code (1)

johnnyvjoyce/simplify-skip-connections 공식 구현

Similar Papers 제목 키워드 기반

Algebraic Neural Networks: Stability to Deformations

2020-09-03 · Alejandro Parada-Mayorga, Alejandro Ribeiro

We study algebraic neural networks (AlgNNs) with commutative algebras which unify diverse architectures such as Euclidean convolutional neural networks, graph neural networks, and group neural networks under the umbrella…

MathDL: Mathematical deep learning for D3R Grand Challenge 4

2019-09-17

We present the performances of our mathematical deep learning (MathDL) models for D3R Grand Challenge 4 (GC4). This challenge involves pose prediction, affinity ranking, and free energy estimation for beta secretase 1 (B…

Deep LearningPose PredictionPrediction

DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling

2020-06-07 · NeurIPS 2020 12 · Moshe Eliasof, Eran Treister

Graph Convolutional Networks (GCNs) have shown to be effective in handling unordered data like point clouds and meshes. In this work we propose novel approaches for graph convolution, pooling and unpooling, inspired from…

RKHS Representation of Algebraic Convolutional Filters with Integral Operators

2026-02-22 · Alejandro Parada-Mayorga, Alejandro Ribeiro, Juan Bazerque arxiv

Integral operators play a central role in signal processing, underpinning classical convolution, and filtering on continuous network models such as graphons. While these operators are traditionally analyzed through spect…

Convolutional Filtering with RKHS Algebras

2024-11-02 · Alejandro Parada-Mayorga, Leopoldo Agorio, Alejandro Ribeiro, Juan Bazerque

In this paper, we develop a generalized theory of convolutional signal processing and neural networks for Reproducing Kernel Hilbert Spaces (RKHS). Leveraging the theory of algebraic signal processing (ASP), we show that…