# Alejandro Parada-MayorgaUniversity of Pennsylvania | UP · Department of Electrical and Systems Engineering

Alejandro Parada-Mayorga

PhD Electrical Engineering

Postdoctoral Researcher at University of Pennsylvania

## About

36

Publications

2,929

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

180

Citations

Introduction

Current research interests: Algebraic signal processing, representation theory, convolutional neural networks and graph limits theory applications in machine learning

Additional affiliations

Education

August 2013 - June 2019

September 2009 - December 2011

May 2003 - May 2009

## Publications

Publications (36)

In this paper we propose a framework to leverage Lie group symmetries on arbitrary spaces exploiting algebraic signal processing (ASP). We show that traditional group convolutions are one particular instantiation of a more general Lie group algebra homomorphism associated to an algebraic signal model rooted in the Lie group algebra $L^{1}(G)$ for g...

Graph convolutional learning has led to many exciting discoveries in diverse areas. However, in some applications, traditional graphs are insufficient to capture the structure and intricacies of the data. In such scenarios, multigraphs arise naturally as discrete structures in which complex dynamics can be embedded. In this paper, we develop convol...

In this paper we introduce and study the algebraic generalization of non commutative convolutional neural networks. We leverage the theory of algebraic signal processing to model convolutional non commutative architectures, and we derive concrete stability bounds that extend those obtained in the literature for commutative convolutional neural netw...

In this paper we propose a pooling approach for convolutional information processing on graphs relying on the theory of graphons and limits of dense graph sequences. We present three methods that exploit the induced graphon representation of graphs and graph signals on partitions of [0, 1]
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:x...

In this paper we propose a pooling approach for convolutional information processing on graphs relying on the theory of graphons and limits of dense graph sequences. We present three methods that exploit the induced graphon representation of graphs and graph signals on partitions of [0, 1] 2 in the graphon space. As a result we derive low dimension...

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 convolution which can be computationally costly. Takin...

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 networks (MGNNs) as stacked and layered structures where...

Graph convolutional learning has led to many exciting discoveries in diverse areas. However, in some applications, traditional graphs are insufficient to capture the structure and intricacies of the data. In such scenarios, multigraphs arise naturally as discrete structures in which complex dynamics can be embedded. In this paper, we develop convol...

In this paper we study the stability properties of aggregation graph neural networks (Agg-GNNs) considering perturbations of the underlying graph. An Agg-GNN is a hybrid architecture where information is defined on the nodes of a graph, but it is processed block-wise by Euclidean CNNs on the nodes after several diffusions on the graph shift operato...

In this paper we provide stability results for algebraic neural networks (AlgNNs) based on non commutative algebras. AlgNNs are stacked layered structures with each layer associated to an algebraic signal model (ASM) determined by an algebra, a vector space, and a homomorphism. Signals are modeled as elements of the vector space, filters are elemen...

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 of algebraic signal processing. An AlgNN is a stacked layered information processing structure where each layer is conformed by a...

With the surge in the volumes and dimensions of data defined in non-Euclidean spaces, graph signal processing (GSP) techniques are emerging as important tools in our understanding of these domains [1]. A fundamental problem for GSP is to determine which nodes play the most important role; so, graph signal sampling and recovery thus become essential...

In this paper we state the basics for a signal processing framework on quiver representations. A quiver is a directed graph and a quiver representation is an assignment of vector spaces to the nodes of the graph and of linear maps between the vector spaces associated to the nodes. Leveraging the tools from representation theory, we propose a signal...

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 are used, like for instance traditional neural netw...

In this work we study the stability of algebraic neural networks (AlgNNs) with commutative algebras which unify CNNs and GNNs under the umbrella of algebraic signal processing. An AlgNN is a stacked layered structure where each layer is conformed by an algebra $\mathcal{A}$, a vector space $\mathcal{M}$ and a homomorphism $\rho:\mathcal{A}\rightarr...

Graph neural networks (GNNs) have been used effectively in different applications involving the processing of signals on irregular structures modeled by graphs. Relying on the use of shift-invariant graph filters, GNNs extend the operation of convolution to graphs. However, the operations of pooling and sampling are still not clearly defined and th...

In the area of graph signal processing, a graph is a set of nodes arbitrarily connected by weighted links; a graph signal is a set of scalar values associated with each node; and sampling is the problem of selecting an optimal subset of nodes from which a graph signal can be reconstructed. This paper proposes the use of spatial dithering on the ver...

In the area of graph signal processing, a graph is a set of nodes arbitrarily connected by weighted links; a graph signal is a set of scalar values associated with each node; and sampling is the problem of selecting an optimal subset of nodes from which a graph signal can be reconstructed. This paper proposes the use of spatial dithering on the ver...

The recently introduced
Spatial Spectral Compressive Spectral Imager (SSCSI)
has been proposed as an alternative to carry out spatial and spectral coding using a binary
ON–OFF
coded aperture. In SSCSI, the pixel pitch size of the coded aperture, as well as its location with respect to the detector array, plays a critical role in the quality of...

The recently introduced Spatial Spectral Compressive Spectral Imager (SSCSI) has been proposed as an alternative to carry out spatial and spectral coding using a binary on-off coded aperture. In SSCSI, the pixel pitch size of the coded aperture, as well as its location with respect to the detector array, play a critical role in the quality of image...

The spatial super-resolution concept is explored on the Spatial Spectral Compressive Hyperspectral Imager as a function of the coded aperture and detector pitch sizes and the coded aperture position s.

The dependency of the number of resolvable bands on the coded aperture positions is proved for the SSCSI. This allows a zooming operation over the spectral dimension of the datacube.

Colored coded aperture optimization in compressive spectral imaging is discussed. Based on the analysis of the coherence of the underlying sensing matrix, a general family of codes is derived. These designs lead to reconstructions of multispectral scenes of better quality than the ones obtained using the traditional random black and white coded ape...

Colored coded apertures have been recently introduced in compressive spectral imaging as a method to improve the quality of image reconstructions in terms of signal to noise ratio. This paper shows that colored coded apertures, in addition, can also provide a higher number of resolvable spectral bands. Colored coded apertures with real and ideal sp...

The use of colored coded apertures in spectral compressive imaging system (CASSI) have been shown to provide advantages in terms of reconstruction fidelity. This work shows that the use of colored coded aperture can also increase the number of resolvable spectral bands.

The Coded Aperture Snapshot Spectral Imaging (CASSI) system captures the three-dimensional (3D) spatio-spectral information of a scene using a set of two-dimensional (2D) random-coded Focal Plane Array (FPA) measurements. A compressive sensing reconstruction algorithm is then used to recover the underlying spatio-spectral 3D data cube. The quality...

A higher-order discretization model for coded aperture-based spectral imaging systems is experimentally demonstrated. The analog light propagation phenomena is better approximated by analyzing the effects of non-linear dispersive elements.

A new pseudorandom coded aperture design framework for multi-frame Coded Aperture Snapshot Spectral
Imaging (CASSI) system is presented. Our previous work determines a matrix system model for multi-frame
CASSI which is used to design sets of spectrally selective coded apertures. Then, the required number of CASSI
measurements is dictated by the des...