Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 27 of 27

Full-Text Articles in Engineering

Flight Simulator Modeling Using Recurrent Neural Networks, Nickolas Sabatini, Andreas Natsis Oct 2020

Flight Simulator Modeling Using Recurrent Neural Networks, Nickolas Sabatini, Andreas Natsis

Undergraduate Research & Mentoring Program

Recurrent neural networks (RNNs) are a form of machine learning used to predict future values. This project uses RNNs tor predict future values for a flight simulator. Coded in Python using the Keras library, the model demonstrates training loss and validation loss, referring to the error when training the model.


An Application Of Deep Learning Models To Automate Food Waste Classification, Alejandro Zachary Espinoza Dec 2019

An Application Of Deep Learning Models To Automate Food Waste Classification, Alejandro Zachary Espinoza

Dissertations and Theses

Food wastage is a problem that affects all demographics and regions of the world. Each year, approximately one-third of food produced for human consumption is thrown away. In an effort to track and reduce food waste in the commercial sector, some companies utilize third party devices which collect data to analyze individual contributions to the global problem. These devices track the type of food wasted (such as vegetables, fruit, boneless chicken, pasta) along with the weight. Some devices also allow the user to leave the food in a kitchen container while it is weighed, so the container weight must also ...


Design Of A Canine Inspired Quadruped Robot As A Platform For Synthetic Neural Network Control, Cody Warren Scharzenberger Jul 2019

Design Of A Canine Inspired Quadruped Robot As A Platform For Synthetic Neural Network Control, Cody Warren Scharzenberger

Dissertations and Theses

Legged locomotion is a feat ubiquitous throughout the animal kingdom, but modern robots still fall far short of similar achievements. This paper presents the design of a canine-inspired quadruped robot named DoggyDeux as a platform for synthetic neural network (SNN) research that may be one avenue for robots to attain animal-like agility and adaptability. DoggyDeux features a fully 3D printed frame, 24 braided pneumatic actuators (BPAs) that drive four 3-DOF limbs in antagonistic extensor-flexor pairs, and an electrical system that allows it to respond to commands from a SNN comprised of central pattern generators (CPGs). Compared to the previous version ...


Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods, Christof Teuscher May 2019

Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods, Christof Teuscher

Student Research Symposium

In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the ...


The Applications Of Grid Cells In Computer Vision, Keaton Kraiger Apr 2019

The Applications Of Grid Cells In Computer Vision, Keaton Kraiger

Undergraduate Research & Mentoring Program

In this study we present a novel method for position and scale invariant object representation based on a biologically-inspired framework. Grid cells are neurons in the entorhinal cortex whose multiple firing locations form a periodic triangular array, tiling the surface of an animal’s environment. We propose a model for simple object representation that maintains position and scale invariance, in which grid maps capture the fundamental structure and features of an object. The model provides a mechanism for identifying feature locations in a Cartesian plane and vectors between object features encoded by grid cells. It is shown that key object ...


Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods Jan 2019

Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods

Undergraduate Research & Mentoring Program

In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the ...


Emulating Balance Control Observed In Human Test Subjects With A Neural Network, Wade William Hilts Jul 2018

Emulating Balance Control Observed In Human Test Subjects With A Neural Network, Wade William Hilts

Dissertations and Theses

Human balance control is a complex feedback system that must be adaptable and robust in an infinitely varying external environment. It is probable that there are many concurrent control loops occurring in the central nervous system that achieve stability for a variety of postural perturbations. Though many engineering models of human balance control have been tested, no models of how these controllers might operate within the nervous system have yet been developed. We have focused on building a model of a proprioceptive feedback loop with simulated neurons. The proprioceptive referenced portion of human balance control has been successfully modeled by ...


Combining Algorithms For More General Ai, Mark Robert Musil May 2018

Combining Algorithms For More General Ai, Mark Robert Musil

Undergraduate Research & Mentoring Program

Two decades since the first convolutional neural network was introduced the AI sub-domains of classification, regression and prediction still rely heavily on a few ML architectures despite their flaws of being hungry for data, time, and high-end hardware while still lacking generality. In order to achieve more general intelligence that can perform one-shot learning, create internal representations, and recognize subtle patterns it is necessary to look for new ML system frameworks. Research on the interface between neuroscience and computational statistics/machine learning has suggested that combined algorithms may increase AI robustness in the same way that separate brain regions specialize ...


Radiation Source Localization By Using Backpropagation Neural Network, Jian Meng, Christof Teuscher, Walt Woods May 2018

Radiation Source Localization By Using Backpropagation Neural Network, Jian Meng, Christof Teuscher, Walt Woods

Student Research Symposium

The most difficult part of the radiation localization is that we cannot use the traditional acoustic localization method to determine where the radiation source is. It’s mainly because the electromagnetic waves are totally different with the sound wave. From the expression of the radioactive intensity, we can tell that the intensity of radiation not only depend on the distance from the radiation but also related to the type of the nuclide. In general, the relationship between the intensity and the distance satisfy the inverse-square law, which is a non-linear relationship. In other words, if we can use the measurement ...


Using Reservoir Computing To Build A Robust Interface With Dna Circuits In Determining Genetic Similarities Between Pathogens, Christopher Neighbor, Christof Teuscher May 2018

Using Reservoir Computing To Build A Robust Interface With Dna Circuits In Determining Genetic Similarities Between Pathogens, Christopher Neighbor, Christof Teuscher

Student Research Symposium

As computational power increases, the field of neural networks has advanced exponentially. In particular recurrent neural networks (RNNs) are being utilized to simulate dynamic systems and to learn to predict time series data. Reservoir computing is an architecture which has the potential to increase training speed while reducing computational costs. Reservoir computing consists of a RNN with a fixed connections “reservoir” while only the output layer is trained. The purpose of this research is to explore the effective use of reservoir computing networks with the eventual application towards use in a DNA based molecular computing reservoir for use in pathogen ...


Early Emerging Pathogen Detection, Mackenzie Wangenstein Jan 2018

Early Emerging Pathogen Detection, Mackenzie Wangenstein

Undergraduate Research & Mentoring Program

A supervised learning technique was employed to identify emerging pathogen species. Portland State University has partnered with the University of New Mexico to take encodings of unknown pathogen molecular structures to determine emerging species.


Video Frame Interpolation Via Adaptive Separable Convolution, Simon Niklaus, Long Mai, Feng Liu Dec 2017

Video Frame Interpolation Via Adaptive Separable Convolution, Simon Niklaus, Long Mai, Feng Liu

Computer Science Faculty Publications and Presentations

Standard video frame interpolation methods first estimate optical flow between input frames and then synthesize an intermediate frame guided by motion. Recent approaches merge these two steps into a single convolution process by convolving input frames with spatially adaptive kernels that account for motion and re-sampling simultaneously. These methods require large kernels to handle large motion, which limits the number of pixels whose kernels can be estimated at once due to the large memory demand. To address this problem, this paper formulates frame interpolation as local separable convolution over input frames using pairs of 1D kernels. Compared to regular 2D ...


Fast And Accurate Sparse Coding Of Visual Stimuli With A Simple, Ultra-Low-Energy Spiking Architecture, Walt Woods, Christof Teuscher Apr 2017

Fast And Accurate Sparse Coding Of Visual Stimuli With A Simple, Ultra-Low-Energy Spiking Architecture, Walt Woods, Christof Teuscher

Electrical and Computer Engineering Faculty Publications and Presentations

Memristive crossbars have become a popular means for realizing unsupervised and supervised learning techniques. Often, to preserve mathematical rigor, the crossbar itself is separated from the neuron capacitors. In this work, we sought to simplify the design, removing extraneous components to consume significantly lower power at a minimal cost of accuracy. This work provides derivations for the design of such a network, named the Simple Spiking Locally Competitive Algorithm, or SSLCA, as well as CMOS designs and results on the CIFAR and MNIST datasets. Compared to a non-spiking model which scored 33% on CIFAR-10 with a single-layer classifier, this hardware ...


Architectures And Algorithms For Intrinsic Computation With Memristive Devices, Jens Bürger Aug 2016

Architectures And Algorithms For Intrinsic Computation With Memristive Devices, Jens Bürger

Dissertations and Theses

Neuromorphic engineering is the research field dedicated to the study and design of brain-inspired hardware and software tools. Recent advances in emerging nanoelectronics promote the implementation of synaptic connections based on memristive devices. Their non-volatile modifiable conductance was shown to exhibit the synaptic properties often used in connecting and training neural layers. With their nanoscale size and non-volatile memory property, they promise a next step in designing more area and energy efficient neuromorphic hardware.

My research deals with the challenges of harnessing memristive device properties that go beyond the behaviors utilized for synaptic weight storage. Based on devices that exhibit ...


Memory And Information Processing In Recurrent Neural Networks, Alireza Goudarzi, Sarah Marzen, Peter Banda, Guy Feldman, Matthew R. Lakin, Christof Teuscher, Darko Stefanovic Apr 2016

Memory And Information Processing In Recurrent Neural Networks, Alireza Goudarzi, Sarah Marzen, Peter Banda, Guy Feldman, Matthew R. Lakin, Christof Teuscher, Darko Stefanovic

Electrical and Computer Engineering Faculty Publications and Presentations

Recurrent neural networks (RNN) are simple dynamical systems whose computational power has been attributed to their short-term memory. Short-term memory of RNNs has been previously studied analytically only for the case of orthogonal networks, and only under annealed approximation, and uncorrelated input. Here for the first time, we present an exact solution to the memory capacity and the task-solving performance as a function of the structure of a given network instance, enabling direct determination of the function-structure relation in RNNs. We calculate the memory capacity for arbitrary networks with exponentially correlated input and further related it to the performance of ...


Information Representation And Computation Of Spike Trains In Reservoir Computing Systems With Spiking Neurons And Analog Neurons, Amin Almassian Mar 2016

Information Representation And Computation Of Spike Trains In Reservoir Computing Systems With Spiking Neurons And Analog Neurons, Amin Almassian

Dissertations and Theses

Real-time processing of space-and-time-variant signals is imperative for perception and real-world problem-solving. In the brain, spatio-temporal stimuli are converted into spike trains by sensory neurons and projected to the neurons in subcortical and cortical layers for further processing.

Reservoir Computing (RC) is a neural computation paradigm that is inspired by cortical Neural Networks (NN). It is promising for real-time, on-line computation of spatio-temporal signals. An RC system incorporates a Recurrent Neural Network (RNN) called reservoir, the state of which is changed by a trajectory of perturbations caused by a spatio-temporal input sequence. A trained, non- recurrent, linear readout-layer interprets the ...


Sparse Adaptive Local Machine Learning Algorithms For Sensing And Analytics, Jack Cannon Jan 2016

Sparse Adaptive Local Machine Learning Algorithms For Sensing And Analytics, Jack Cannon

Undergraduate Research & Mentoring Program

The goal of digital image processing is to capture, transmit, and display images as efficiently as possible. Such tasks are computationally intensive because an image is digitally represented by large amounts of data. It is possible to render an image by reconstructing it with a subset of the most relevant data. One such procedure used to accomplish this task is commonly referred to as sparse coding. For our purpose, we use images of handwritten digits that are presented to an artificial neural network. The network implements Rozell's locally competitive algorithm (LCA) to generate a sparse code. This sparse code ...


A Brief Review Of Speaker Recognition Technology, Clark D. Shaver, John M. Acken Jan 2016

A Brief Review Of Speaker Recognition Technology, Clark D. Shaver, John M. Acken

Electrical and Computer Engineering Faculty Publications and Presentations

This paper reviews the development of speaker recognition systems from pre-computing days to current trends. Advances in various sciences which have allowed autonomous speaker recognition systems to become a practical means of identity authentication are also reviewed.


Modeling And Experimental Demonstration Of A Hopfield Network Analog-To-Digital Converter With Hybrid Cmos/Memristor Circuits, Xinjie Guo, Farnood Merrikh-Bayat, Ligang Gao, Brian D. Hoskins, Fabien Alibart, Bernabe Linares-Barranco, Luke Theogarajan, Christof Teuscher, Dmitri B. Strukov Dec 2015

Modeling And Experimental Demonstration Of A Hopfield Network Analog-To-Digital Converter With Hybrid Cmos/Memristor Circuits, Xinjie Guo, Farnood Merrikh-Bayat, Ligang Gao, Brian D. Hoskins, Fabien Alibart, Bernabe Linares-Barranco, Luke Theogarajan, Christof Teuscher, Dmitri B. Strukov

Electrical and Computer Engineering Faculty Publications and Presentations

The purpose of this work was to demonstrate the feasibility of building recurrent artificial neural networks with hybrid complementary metal oxide semiconductor (CMOS)/memristor circuits. To do so, we modeled a Hopfield network implementing an analog-to-digital converter (ADC) with up to 8 bits of precision. Major shortcomings affecting the ADC's precision, such as the non-ideal behavior of CMOS circuitry and the specific limitations of memristors, were investigated and an effective solution was proposed, capitalizing on the in-field programmability of memristors. The theoretical work was validated experimentally by demonstrating the successful operation of a 4-bit ADC circuit implemented with discrete ...


Computational Capacity And Energy Consumption Of Complex Resistive Switch Networks, Jens Bürger, Alireza Goudarzi, Darko Stefanovic, Christof Teuscher Dec 2015

Computational Capacity And Energy Consumption Of Complex Resistive Switch Networks, Jens Bürger, Alireza Goudarzi, Darko Stefanovic, Christof Teuscher

Electrical and Computer Engineering Faculty Publications and Presentations

Resistive switches are a class of emerging nanoelectronics devices that exhibit a wide variety of switching characteristics closely resembling behaviors of biological synapses. Assembled into random networks, such resistive switches produce emerging behaviors far more complex than that of individual devices. This was previously demonstrated in simulations that exploit information processing within these random networks to solve tasks that require nonlinear computation as well as memory. Physical assemblies of such networks manifest complex spatial structures and basic processing capabilities often related to biologically-inspired computing. We model and simulate random resistive switch networks and analyze their computational capacities. We provide a ...


Computational Capabilities Of Leaky Integrate-And-Fire Neural Networks For Liquid State Machines, Amin Almassian, Christof Teuscher May 2013

Computational Capabilities Of Leaky Integrate-And-Fire Neural Networks For Liquid State Machines, Amin Almassian, Christof Teuscher

Student Research Symposium

We analyze the computational capability of Leaky Integrate-and-Fire (LIF) Neural Networks used as a reservoir (liquid) in the framework of Liquid State Machines (LSM). Maass et. al. investigated LIF neurons in LSM and their results showed that they are capable of noise-robust, parallel, and real-time computation. However, it still remains an open question how the network topology affects the computational capability of a reservoir. To address that question, we investigate the performance of the reservoir as a function of the average reservoir connectivity. We also show that the dynamics of the LIF reservoir is sensitive to changes in the average ...


Blackfingers A Sophisticated Hand Prothesis, Michele Folgheraiter, Giuseppina Gini, Marek Perkowski, Mikhail Pivtoraiko Apr 2003

Blackfingers A Sophisticated Hand Prothesis, Michele Folgheraiter, Giuseppina Gini, Marek Perkowski, Mikhail Pivtoraiko

Electrical and Computer Engineering Faculty Publications and Presentations

Our goal is to develop the low level control system for an artificial hand ”Blackfingers”. Blackfingers was thought to have two main applications: as humanoid robot’s hand or as a human hand prothesis. In this last application our intent is to realize a device more sophisticated respect the actual commerce prothesis. Also in our intention is to use some biological paradigms to create a human like reflex control easy to be interfaced also with the human nervous system. In this paper we illustrate the properties and the morphology of a human like neural reflex controller, used to set the ...


Le Bio Wall : Un Tissue Informatique Pour Le Prototypage De Systèmes Bio-Inspirés, Andre Stauffer, Daniel Mange, Gianluca Tempesti, Christof Teuscher Apr 2002

Le Bio Wall : Un Tissue Informatique Pour Le Prototypage De Systèmes Bio-Inspirés, Andre Stauffer, Daniel Mange, Gianluca Tempesti, Christof Teuscher

Electrical and Computer Engineering Faculty Publications and Presentations

Dans cet article, nous décrivons le BioWall, un tissu informatique reconfigurable géant développé dans le but d’y implémenter des machines mettant en oeuvre les principes de notre projet Embryonique. Bien que ses dimensions et ses caractéristiques en font d’abord un objet de démonstration publique, le BioWall constitue également un outil de recherche précieux, du fait que sa faculté de reprogrammation et sa structure cellulaire s’adaptent parfaitement à l’implémentation de toutes sortes de systèmes bioinspirés. Pour illustrer ces capacités, nous décrivons un ensemble d’applications qui reflètent différentes sources d’inspiration biologique allant des systèmes biologiques ontogénétiques ...


Automatic Tuning Of Integrated Filters Using Neural Networks, Lutz Henning Lenz Jul 1993

Automatic Tuning Of Integrated Filters Using Neural Networks, Lutz Henning Lenz

Dissertations and Theses

Component values of integrated filters vary considerably due to· manufacturing tolerances and environmental changes. Thus it is of major importance that the components of an integrated filter be electronically tunable. The method explored in this thesis is the transconductance-C-method. A method of realizing higher-order filters is to use a cascade structure of second-order filters. In this context, a method of tuning second-order filters becomes important The research objective of this thesis is to determine if the Neural Network methodology can be used to facilitate the filter tuning process for a second-order filter (realized via the transconductance-C-method). Since this thesis is ...


A Gaze-Addressing Communication System Using Artificial Neural Networks, Gabriel Baud-Bovy Jan 1992

A Gaze-Addressing Communication System Using Artificial Neural Networks, Gabriel Baud-Bovy

Dissertations and Theses

Severe motor disabilities can render a person almost completely incapable of communication. Nevertheless, in many cases, the sensory systems are intact and the eye movements are still under good control. In these cases, one can use a device such as the Brain Response Interface (BRI) to command a remote control (e.g. room temperature, bed position), a word-processor, a speech synthesizer, and so on.


Neural Network Character Recognition With A 2-D Fourier Transform Preprocessor, Daqiao Du Jan 1991

Neural Network Character Recognition With A 2-D Fourier Transform Preprocessor, Daqiao Du

Dissertations and Theses

In pattern recognition applications, it is usually important that the same identification be given for a pattern, independent of a variety of positions, rotations and /or distortions of the pattern within the recognition device's field of view. This research relates to development of a preprocessor for a neural network character recognition system, where the role of the preprocessor is to assist in minimizing the difficulties related to variations of position and rotations of a character within the field of view. The preprocessor explored here was suggested in 1970' (Lendaris & Stanly, 1970), and is implemented here with more recent advances ...


A New Design Approach For Numeric-To-Symbolic Conversion Using Neural Networks, Zibin Tang Jan 1991

A New Design Approach For Numeric-To-Symbolic Conversion Using Neural Networks, Zibin Tang

Dissertations and Theses

A new approach is proposed which uses a combination of a Backprop paradigm neural network along with some perceptron processing elements performing logic operations to construct a numeric-to-symbolic converter. The design approach proposed herein is capable of implementing a decision region defined by a multi-dimensional, non-linear boundary surface. By defining a "two-valued" subspace of the boundary surface, a Backprop paradigm neural network is used to model the boundary surf ace. An input vector is tested by the neural network boundary model (along with perceptron logic gates) to determine whether the incoming vector point is within the decision region or not ...