Physical Sciences and Mathematics Commons^™

Growing Reservoir Networks Using The Genetic Algorithm Deep Hyperneat, Nancy L. Mackenzie

Student Research Symposium

Typical Artificial Neural Networks (ANNs) have static architectures. The number of nodes and their organization must be chosen and tuned for each task. Choosing these values, or hyperparameters, is a bit of a guessing game, and optimizing must be repeated for each task. If the model is larger than necessary, this leads to more training time and computational cost. The goal of this project is to evolve networks that grow according to the task at hand. By gradually increasing the size and complexity of the network to the extent that the task requires, we will build networks that are more …

Development Of A Design Guideline For Pile Foundations Subjected To Liquefaction-Induced Lateral Spreading, Milad Souri, Arash Khosravifar

Student Research Symposium

Past earthquakes confirmed that seismically induced kinematic loads from soil lateral spreading and inertial loads from structure can cause severe damages to pile foundations. The research questions are:

• How to combine inertial and kinematic loads in design of pile foundations in liquefied soil?
• How the combination of inertia and kinematics changes with depth?
• How this combination is affected by long-duration earthquakes?
• How this combination affects inelastic demands in piles?

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 evaluation of …

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 …

Find, Build, And Export Information For 3d Printing Of Your Favorite Molecules And Crystal Structures At Two Dedicated Websites, Paul R. Destefano, Peter Moeck

Student Research Symposium

As 3D printers require instructions, the Nano-Crystallography Group at Portland State University is creating two websites (http://nanocrystallography.org/3dconvert/ and http://nanocrystallography.research.pdx.edu/3d-print-files/convert/) where such instructions are created, interactively, for the atomic arrangements of virtually all known molecules and crystals.

We will prepare a "pipeline" into which crystallographic information enters from two curated open access crystallographic databases, is manipulated to create the desired 3D models, and then is exported in either STL format (the standard for monochrome 3D printing) or VRML/X3D (the ISO successor to STL). The two aforementioned databases are the North-American mirror of the Crystallography Open Database (http://nanocrystallography.org) …

Design, Construction, And Utilization Of Physical Vapor Deposition Systems For Medical Sensor Fabrication, Nicholas Sayre, Abdul Almetairi, Alex Chally, Joe Kowalski, Erik J. Sánchez

Student Research Symposium

The development of a novel blood glucose sensor is realized through construction of a homemade plasma coating system and utilization of semiconductor manufacturing processes in a small scale cleanroom environment. Photolithography, plasma sputtering, chemical etching and thin film measurement technologies are used in the medical sensor fabrication process. General process flow will be discussed, and system design and the plasma sputtering process will be presented as it is achieved by the system currently under development.