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

Engineering Commons

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

Portland State University

Machine learning

Discipline
Publication Year
Publication
Publication Type

Articles 1 - 30 of 30

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.


Empirical Analysis Of Cbow And Skip Gram Nlp Models, Tejas Menon Jul 2020

Empirical Analysis Of Cbow And Skip Gram Nlp Models, Tejas Menon

University Honors Theses

CBOW and Skip Gram are two NLP techniques to produce word embedding models that are accurate and performant. They were invented in the seminal paper by T. Mikolov et al. and have since observed optimizations such as negative sampling and subsampling. This paper implements a fully-optimized version of these models using Py-Torch and runs them through a toy sentiment/subject analysis. It is weakly observed that different corpus types affect the skew of work embeddings such that fictional corpus are better suited for sentiment analysis and non-fictional for subject analysis.


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 ...


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 ...


Diagnostic Imaging Of Structural Concrete Using Ground Penetrating Radar And Ultrasonic Array, Sina Mehdinia, Thomas Schumacher, Eric Wan, Xubo Song May 2019

Diagnostic Imaging Of Structural Concrete Using Ground Penetrating Radar And Ultrasonic Array, Sina Mehdinia, Thomas Schumacher, Eric Wan, Xubo Song

Student Research Symposium

Structural concrete is the most widely used construction material in the world. Many structures critical to a society such as bridges, hospitals, and airports are built with concrete. While this material is well understood from a mechanical design point of view, still no accurate quantitative tools exist to assess it for damage and deterioration. This is of particular concern for an urban area like Portland with a mega-thrust earthquake waiting to occur. Non-destructive evaluation tools that can quickly and accurately give a full picture of the integrity of structural concrete elements will be key to help plan effective and safe ...


Explanation Methods For Neural Networks, Jack H. Chen, Christof Teuscher May 2019

Explanation Methods For Neural Networks, Jack H. Chen, Christof Teuscher

Student Research Symposium

Neural Networks (NNs) have become a basis of almost all state-of-the-art machine learning algorithms and classifiers. While NNs have been shown to generalize well to real-world examples, researchers have struggled to show why they work on an intuitive level. We designed several methods to explain the decisions of two state-of-the-art NN classifiers, ResNet and an All-CNN, in the context of the Japanese Society of Radiological Technology (JSRT) lung nodule dataset and the CIFAR-10 image dataset. Leading explanation methods LIME and Grad-CAM generate variations of heat maps which represent the regions of the input determined salient by the NN. We analyze ...


Reliable Explanations Via Adversarial Examples On Robust Networks, Walt Woods, Jack H. Chen, Christof Teuscher May 2019

Reliable Explanations Via Adversarial Examples On Robust Networks, Walt Woods, Jack H. Chen, Christof Teuscher

Student Research Symposium

Neural Networks (NNs) are increasingly used as the basis of advanced machine learning techniques in sensitive fields such as autonomous vehicles and medical imaging. However, NNs have been found vulnerable to a class of imperceptible attacks, called adversarial examples, which arbitrarily alter the output of the network. To close the schism between needing reliability in real-world applications and the fragility of NNs, we propose a new method for stabilizing networks, and show that as an added bonus, our technique results in reliable, high-fidelity explanations for the NN's decision. Compared to the state-of-the-art, this technique increased the area under the ...


Spectral Clustering For Electrical Phase Identification Using Advanced Metering Infrastructure Voltage Time Series, Logan Blakely Jan 2019

Spectral Clustering For Electrical Phase Identification Using Advanced Metering Infrastructure Voltage Time Series, Logan Blakely

Dissertations and Theses

The increasing demand for and prevalence of distributed energy resources (DER) such as solar power, electric vehicles, and energy storage, present a unique set of challenges for integration into a legacy power grid, and accurate models of the low-voltage distribution systems are critical for accurate simulations of DER. Accurate labeling of the phase connections for each customer in a utility model is one area of grid topology that is known to have errors and has implications for the safety, efficiency, and hosting capacity of a distribution system. This research presents a methodology for the phase identification of customers solely using ...


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 ...


Real-Time Object Detection And Tracking On Drones, Tu Le May 2018

Real-Time Object Detection And Tracking On Drones, Tu Le

Undergraduate Research & Mentoring Program

Unmanned aerial vehicles, also known as drones, have been more and more widely used in recent decades because of their mobility. They appear in many applications such as farming, search and rescue, entertainment, military, and so on. Such high demands for drones lead to the need of developments in drone technologies. Next generations of commercial and military drones are expected to be aware of surrounding objects while flying autonomously in different terrains and conditions. One of the biggest challenges to drone automation is the ability to detect and track objects of interest in real-time. While there are many robust machine ...


From A Locally Competitive Algorithm To Sensory Relevance Models, Walter Woods Mar 2018

From A Locally Competitive Algorithm To Sensory Relevance Models, Walter Woods

Electrical and Computer Engineering PhD Day

This poster addresses the development of a new Machine Learning (ML) mechanism, the Sensory Relevance Model (SRM), as a means of splitting information processing tasks into two sub-tasks with more intuitive properties. Specifically, SRMs are a front-end for other ML techniques, re-mapping the input data to a similar space with significantly more sparsity, achieved through the transformation and suppression of inputs irrelevant to the task. Prior work has attempted to reveal this information for Neural Networks (NNs) either as a post-processing step via saliency maps or through a simple masking of the input achieved with a dot product (so-called ``attention ...


Hierarchical Random Boolean Network Reservoirs, Sai Kiran Cherupally Feb 2018

Hierarchical Random Boolean Network Reservoirs, Sai Kiran Cherupally

Dissertations and Theses

Reservoir Computing (RC) is an emerging Machine Learning (ML) paradigm. RC systems contain randomly assembled computing devices and can be trained to solve complex temporal tasks. These systems are computationally cheaper to train than other ML paradigms such as recurrent neural networks, and they can also be trained to solve multiple tasks simultaneously. Further, hierarchical RC systems with fixed topologies, were shown to outperform monolithic RC systems by up to 40% when solving temporal tasks. Although the performance of monolithic RC networks was shown to improve with increasing network size, building large monolithic networks may be challenging, for example because ...


Water Quality Factor Prediction Using Supervised Machine Learning, Kathleen Joslyn Jan 2018

Water Quality Factor Prediction Using Supervised Machine Learning, Kathleen Joslyn

REU Final Reports

The objective of this research is to explore prediction accuracy of water quality factors, with techniques and algorithms in machine learning consisting of a variation of support vector machines - Support Vector Regression (SVR) and the gradient boosting algorithm Extreme Gradient Boosting (XGBoost). Both the XGBoost and SVR algorithms were used to predict nine different factors with success rates ranging from 79% to 99%. Parameters of these algorithms were also explored to test the prediction accuracy levels of individual water quality factors. These parameters included normalizing the data, filling missing data points, and training and testing on a large set of ...


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 On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell Nov 2017

Fast On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell

Computer Science Faculty Publications and Presentations

A major goal of computer vision is to enable computers to interpret visual situations—abstract concepts (e.g., “a person walking a dog,” “a crowd waiting for a bus,” “a picnic”) whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. In this paper, we propose a novel method for prior learning and active object localization for this kind of knowledge-driven search in static images. In our system, prior situation knowledge is captured by a set of flexible, kernel-based density estimations— a situation model—that represent the expected spatial structure of the ...


Building Intelligence In The Automated Traffic Signal Performance Measures With Advanced Data Analytics, Tingting Huang, Subhadipto Poddar, Chris Aguilar, Anuj Sharma, Edward J. Smaglik, Sirisha Kothuri, Peter Koonce Aug 2017

Building Intelligence In The Automated Traffic Signal Performance Measures With Advanced Data Analytics, Tingting Huang, Subhadipto Poddar, Chris Aguilar, Anuj Sharma, Edward J. Smaglik, Sirisha Kothuri, Peter Koonce

Civil and Environmental Engineering Faculty Publications and Presentations

Automated traffic signal performance measures (ATSPMs) are an effort to equip traffic signal controllers with high-resolution data-logging capabilities and utilize this data to generate performance measures. These measures allow practitioners to improve operations as well as to maintain and operate their systems in a safe and efficient manner. Although these measures have changed the way that operators manage their systems, several shortcomings of the tool, identified by talking with signal operators, are a lack of data quality control and the extent of resources required to properly use the tool for system-wide management. To address these shortcomings, intelligent traffic signal performance ...


Lithography Hotspot Detection, Jea Woo Park Jul 2017

Lithography Hotspot Detection, Jea Woo Park

Dissertations and Theses

The lithography process for chip manufacturing has been playing a critical role in keeping Moor's law alive. Even though the wavelength used for the process is bigger than actual device feature size, which makes it difficult to transfer layout patterns from the mask to wafer, lithographers have developed a various technique such as Resolution Enhancement Techniques (RETs), Multi-patterning, and Optical Proximity Correction (OPC) to overcome the sub-wavelength lithography gap.

However, as feature size in chip design scales down further to a point where manufacturing constraints must be applied to early design phase before generating physical design layout. Design for ...


Bayesian Optimization For Refining Object Proposals, Anthony D. Rhodes, Jordan Witte, Melanie Mitchell, Bruno Jedynak Mar 2017

Bayesian Optimization For Refining Object Proposals, Anthony D. Rhodes, Jordan Witte, Melanie Mitchell, Bruno Jedynak

Computer Science Faculty Publications and Presentations

We develop a general-purpose algorithm using a Bayesian optimization framework for the efficient refinement of object proposals. While recent research has achieved substantial progress for object localization and related objectives in computer vision, current state-of-the-art object localization procedures are nevertheless encumbered by inefficiency and inaccuracy. We present a novel, computationally efficient method for refining inaccurate bounding-box proposals for a target object using Bayesian optimization. Offline, image features from a convolutional neural network are used to train a model to predict an object proposal’s offset distance from a target object. Online, this model is used in a Bayesian active search ...


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 ...


Training Set Design For Test Removal Classication In Ic Test, Nagarjun Hassan Ranganath Oct 2014

Training Set Design For Test Removal Classication In Ic Test, Nagarjun Hassan Ranganath

Dissertations and Theses

This thesis reports the performance of a simple classifier as a function of its training data set. The classifier is used to remove analog tests and is named the Test Removal Classifier (TRC).

The thesis proposes seven different training data set designs that vary by the number of wafers in the data set, the source of the wafers and the replacement scheme of the wafers. The training data set size ranges from a single wafer to a maximum of five wafers. Three of the training data sets include wafers from the Lot Under Test (LUT). The training wafers in the ...


Reward-Driven Training Of Random Boolean Network Reservoirs For Model-Free Environments, Padmashri Gargesa Mar 2013

Reward-Driven Training Of Random Boolean Network Reservoirs For Model-Free Environments, Padmashri Gargesa

Dissertations and Theses

Reservoir Computing (RC) is an emerging machine learning paradigm where a fixed kernel, built from a randomly connected "reservoir" with sufficiently rich dynamics, is capable of expanding the problem space in a non-linear fashion to a higher dimensional feature space. These features can then be interpreted by a linear readout layer that is trained by a gradient descent method. In comparison to traditional neural networks, only the output layer needs to be trained, which leads to a significant computational advantage. In addition, the short term memory of the reservoir dynamics has the ability to transform a complex temporal input state ...


Creating Insanity In Learning Systems: Addressing Ambiguity Effects Of Predicting Non-Linear Continuous Valued Functions With Reconstructabilty Analysis From Large Categorically Valued Input Data Sets, William D. Eisenhauer Dec 2009

Creating Insanity In Learning Systems: Addressing Ambiguity Effects Of Predicting Non-Linear Continuous Valued Functions With Reconstructabilty Analysis From Large Categorically Valued Input Data Sets, William D. Eisenhauer

Systems Science Friday Noon Seminar Series

Being told to give two different, and potentially counter, responses to the same stimulus can set up a double bind in humans, leading to a type of insanity. So what how do you deal with it when it comes up quite frequently in modeling through simplification and removal of predictive variables?

In his current dissertation research Ike Eisenhauer is using reconstructability analysis to implement K-System, U-System, and B-System approaches to predict a continuously valued function through discrete categorically valued input variables [e.g. textual data]. One of the key issues is how to address the inability of K-Systems and U-Systems ...


Quantum Inductive Learning And Quantum Logic Synthesis, Martin Lukac Jan 2009

Quantum Inductive Learning And Quantum Logic Synthesis, Martin Lukac

Dissertations and Theses

Since Quantum Computer is almost realizable on large scale and Quantum Technology is one of the main solutions to the Moore Limit, Quantum Logic Synthesis (QLS) has become a required theory and tool for designing Quantum Logic Circuits. However, despite its growth, there is no any unified aproach to QLS as Quantum Computing is still being discovered and novel applications are being identified.

The intent of this study is to experimentally explore principles of Quantum Logic Synthesis and its applications to Inductive Machine Learning. Based on algorithmic approach, I first design a Genetic Algorithm for Quantum Logic Synthesis that is ...


Efficient Decomposition Of Large Fuzzy Functions And Relations, Paul Burkey, Marek Perkowski Mar 2003

Efficient Decomposition Of Large Fuzzy Functions And Relations, Paul Burkey, Marek Perkowski

Electrical and Computer Engineering Faculty Publications and Presentations

This paper presents a new approach to decomposition of fuzzy functions. A tutorial background on fuzzy logic representations is first given to emphasize next the simplicity and generality of this new approach. Ashenhurst-like decomposition of fuzzy functions was discussed in [3] but it was not suitable for programming and was not programmed. In our approach, fuzzy functions are converted to multiple-valued functions and decomposed using an mv decomposer. Then the decomposed multiple-valued functions are converted back to fuzzy functions. This approach allows for Curtis-like decompositions with arbitrary number of intermediate fuzzy variables, that have been not presented for fuzzy functions ...


A New Approach To Robot’S Imitation Of Behaviors By Decomposition Of Multiple-Valued Relations, Uland Wong, Marek Perkowski Sep 2002

A New Approach To Robot’S Imitation Of Behaviors By Decomposition Of Multiple-Valued Relations, Uland Wong, Marek Perkowski

Electrical and Computer Engineering Faculty Publications and Presentations

Relation decomposition has been used for FPGA mapping, layout optimization, and data mining. Decision trees are very popular in data mining and robotics. We present relation decomposition as a new general-purpose machine learning method which generalizes the methods of inducing decision trees, decision diagrams and other structures. Relation decomposition can be used in robotics also in place of classical learning methods such as Reinforcement Learning or Artificial Neural Networks. This paper presents an approach to imitation learning based on decomposition. A Head/Hand robot learns simple behaviors using features extracted from computer vision, speech recognition and sensors.


Implicit Algorithms For Multi-Valued Input Support Manipulation, Alan Mishchenko, Craig Files, Marek Perkowski, Bernd Steinbach, Christina Dorotska Sep 2001

Implicit Algorithms For Multi-Valued Input Support Manipulation, Alan Mishchenko, Craig Files, Marek Perkowski, Bernd Steinbach, Christina Dorotska

Electrical and Computer Engineering Faculty Publications and Presentations

We present an implicit approach to solve problems arising in decomposition of incompletely specified multi-valued functions and relations. We introduce a new representation based on binaryencoded multi-valued decision diagrams (BEMDDs). This representation shares desirable properties of MDDs, in particular, compactness, and is applicable to weakly-specified relations with a large number of output values. This makes our decomposition approach particularly useful for data mining and machine learning. Using BEMDDs to represent multi-valued relations we have developed two complementary input support minimization algorithms. The first algorithm is efficient when the resulting support contains almost all initial variables; the second is efficient when ...


Decomposition Of Relations: A New Approach To Constructive Induction In Machine Learning And Data Mining -- An Overview, Marek Perkowski, Stanislaw Grygiel May 2001

Decomposition Of Relations: A New Approach To Constructive Induction In Machine Learning And Data Mining -- An Overview, Marek Perkowski, Stanislaw Grygiel

Electrical and Computer Engineering Faculty Publications and Presentations

This is a review paper that presents work done at Portland State University and associated groups in years 1989 - 2001 in the area of functional decomposition of multivalued functions and relations, as well as some applications of these methods.


Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson Mar 1999

Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson

Electrical and Computer Engineering Faculty Publications and Presentations

"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only.


Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson Jan 1999

Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson

Electrical and Computer Engineering Faculty Publications and Presentations

"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only. Various approaches to supervised inductive ...