Alejandro Parada-Mayorga

Alejandro Parada-Mayorga
University of Pennsylvania | UP · Department of Electrical and Systems Engineering

PhD Electrical Engineering
Postdoctoral Researcher at University of Pennsylvania

About

25
Publications
2,050
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
81
Citations
Introduction
Current research interests: Algebraic signal processing, representation theory, convolutional neural networks and graph limits theory applications in machine learning
Additional affiliations
September 2013 - June 2019
University of Delaware
Position
  • Research Assistant
January 2011 - December 2012
Industrial University of Santander
Position
  • Lecturer
Description
  • Lecturer in the courses: Digital Signal Processing and Digital Image processing
Education
August 2013 - June 2019
University of Delaware
Field of study
  • Electrical Engineering
September 2009 - December 2011
Industrial University of Santander
Field of study
  • Electrical Engineering
May 2003 - May 2009
Industrial University of Santander
Field of study
  • Electrical Engineering

Publications

Publications (25)
Preprint
Full-text available
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...
Article
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...
Article
Full-text available
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...
Preprint
Full-text available
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...
Preprint
Full-text available
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...
Preprint
Full-text available
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...
Preprint
Full-text available
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...
Preprint
Full-text available
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...
Article
Full-text available
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...
Article
The recently introduced \textit{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...
Preprint
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...
Conference Paper
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.
Conference Paper
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.
Article
Full-text available
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...
Article
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...
Conference Paper
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.
Article
Full-text available
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...
Conference Paper
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.
Conference Paper
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...

Network

Cited By