Alejandro Parada-Mayorga — accepted AI-conference papers

2025

DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images

Chen Liu, Danqi Liao, Alejandro Parada-Mayorga, Alejandro Ribeiro, Marcello DiStasio, Smita Krishnaswamy

ICASSP 2025accepted

The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for biomedical research and clinical diagnostics. However, accurately annotating densely packed information in these images remains a major challenge. To address t…

Cited by 0 Source ↗Scholar ↗

2024

Non Commutative Convolutional Signal Models in Neural Networks: Stability to Small Deformations

Alejandro Parada-Mayorga, Landon Butler, Alejandro Ribeiro

ICASSP 2024accepted

In this paper we discuss the results recently published in [1] about algebraic signal models (ASMs) based on non commutative algebras and their use in convolutional neural networks. Relying on the general tools from algebraic signal processing (ASP), we study the filtering and stability properties o…

Cited by 0 Source ↗Scholar ↗

2023

Algebraic Convolutional Filters on Lie Group Algebras

Harshat Kumar, Alejandro Parada-Mayorga, Alejandro Ribeiro

ICASSP 2023accepted

Group convolutional neural networks are a useful tool for utilizing symmetries known to be in a signal; however, they require that the signal is defined on the group itself. Existing approaches either work directly with group signals, or they impose a lifting step with heuristics to compute the conv…

Cited by 0 Source ↗Scholar ↗

2023

Learning with Multigraph Convolutional Filters

Landon Butler, Alejandro Parada-Mayorga, Alejandro Ribeiro

ICASSP 2023accepted

In this paper, we introduce a convolutional architecture to perform learning when information is supported on multigraphs. Exploiting algebraic signal processing (ASP), we propose a convolutional signal processing model on multigraphs (MSP). Then, we introduce multigraph convolutional neural network…

Cited by 0 Source ↗Scholar ↗

2021

Stability of Algebraic Neural Networks to Small Perturbations

Alejandro Parada-Mayorga, Alejandro Ribeiro

ICASSP 2021accepted

Algebraic neural networks (AlgNNs) are composed of a cascade of layers each one associated to and algebraic signal model, and information is mapped between layers by means of a nonlinearity function. AlgNNs provide a generalization of neural network architectures where formal convolution operators a…

Cited by 0 Source ↗Scholar ↗