About

Welcome to my website!. I am a postdoctoral researcher at University of Pennsylvania under the supervision of professor Alejandro Ribeiro. I received my Ph.D degree in electrical engineering from University of Delaware, DE, USA, and the B.Sc. and the Master’s degree in electrical engineering from Industrial University of Santander, Colombia.

Research Interests

I love and have an interest in abstraction and branches of mathematics that tend to high levels of abstraction. Consequently, I have interests in areas such as representation theory, category theory, topology, functional analysis, algebraic geometry and recently tropical geometry. My research vision, relies on exploiting tools from these areas not only to visualize and represent information in ways that can provide new insights about how to do processing, but also to find new ways in which to teach and communicate ideas, concepts and methods useful to solve problems in engineering. Nowadays, my interests aligned naturally with geometric deep learning, where I have been recently exploiting tools from representation theory (see our papers: paper1, paper2) and graph limit theory (see our paper) for the analysis of convolutional architectures and graph neural networks. In the near term I will be working in topological signal processing and topological data analysis too. More information about my recent research is available here.

News

  • New paper accepted: A. Parada-Mayorga and A. Ribeiro, “Stability of Algebraic Neural Networks to Small Perturbations” ICASSP 2021. [link]
  • New talk about our work “Graphon Pooling in Graph Neural Networks” at EUSIPCO2020. [video][slides]
  • New online material available about algebraic neural networks. This is a lecture part of the Penn course in Graph Neural Networks [video]
  • New preprint is out!: A. Parada-Mayorga, H. Riess, A. Ribeiro, and Robert Ghrist, “Quiver Signal Processing (QSP)”(submitted)[link]
  • My joint work with professor Alejandro Ribeiro about “Algebraic Neural Networks: Stability to Deformations” was presented at the Workshop on Equivariance and Data Augmentation at University of Pennsylvania, September 4, 2020. [video][slides]
  • New preprint is out!: A. Parada-Mayorga and A. Ribeiro, “Algebraic Neural Networks: Stability to Deformations”(submitted to IEEE Transactions on Signal Processing)[link].
  • Coming soon: D. Guillot, A. Parada-Mayorga, S. Cioaba and G.R. Arce, ”Uniqueness sets in the Paley-Wiener Space of Cographs”.
  • New paper accepted: D.L. Lau, G. R. Arce, A. Parada-Mayorga, D. Dapena, K. Pena-Pena, “Blue-Noise Sampling of Graph and Multigraph Signals” (Submitted to the Special Issue of the IEEE Signal Processing Magazine On Graph Signal Processing: Foundations and Emerging Directions).
  • New paper accepted: A. Parada-Mayorga, L. Ruiz and A. Ribeiro, “Graphon Pooling in Graph Neural Networks”. [link]