Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Machine Learning (3)
- Algorithm (1)
- Algorithmic Composition (1)
- Algorithms (1)
- Architectural models (1)
-
- Artificial Intelligence (1)
- Artificial Intelligence; Mancala (Game) (1)
- BayesWave (1)
- Computer Vision (1)
- Computer algorithms; Machine learning; Artificial intelligence; Neural networks (Computer science); Computer music (1)
- Computing (1)
- Conditional Variational Autoencoder (1)
- Crawler (1)
- Data Augmentation (1)
- Game-Solving (1)
- Generative AI (1)
- Gravitational Waves (1)
- Gravitational waves; BayesWave; LIGO (1)
- Hidden Services (1)
- Information Encoding (1)
- Interconnectivity (1)
- Invisible Web; Tor (Anonymity network) (1)
- LIGO (1)
- Machine learning; Computer algorithm; Neural architecture search (1)
- Machine learning; Database management; Computer vision; Conditional Variational Autoencoder; Data augmentation (1)
- Mancala (1)
- Mean Neuronal Firing Rate (1)
- Motor (1)
- Music Generation (1)
- Neural Architecture Search (1)
Articles 1 - 8 of 8
Full-Text Articles in Engineering
Art To Influence Creativity In Algorithmic Composition, Tyler Braithwaite
Art To Influence Creativity In Algorithmic Composition, Tyler Braithwaite
Honors Theses
Advances in Recurrent Neural Network (RNN) techniques have caused an explosion of problems posed that revolve around the mass analysis and generation of sequential data, including symbolic music. Building off the work of Nathaniel Patterson’s Musical Autocomplete: An LSTM Approach, we extend this problem of continuing a composition by examining the creative impact that injecting latent-space encoded image data, specifically fine art from the WikiArt Dataset, has on the musical output of RNN architectures designed for autocomplete. For comparison purposes with Patterson, we will also be using a corpus of Erik Satie’s piano music for training, validation, and testing.
Conditional Variational Autoencoder (Cvae) For The Augmentation Of Ecl Biosensor Data, Matthew Dulcich
Conditional Variational Autoencoder (Cvae) For The Augmentation Of Ecl Biosensor Data, Matthew Dulcich
Honors Theses
Machine Learning (ML) is vastly improving the world, from computer vision to fully self-driving cars, we are now able accomplish objectives that were thought to only be dreams. In order to train ML models accurately, they require mountains of information to work with, but sometimes it becomes impossible to collect the data needed, so we turn to data augmentation. In this project we use a conditional variational auto encoder to supplement the original video electrochemiluminescence biosensor dataset, in order to increase the accuracy of a future classification model. In other words, using a cVAE we will create unique realistic videos …
Exploring The Efficiency Of Neural Architecture Search (Nas) Modules, Joshua Dulcich
Exploring The Efficiency Of Neural Architecture Search (Nas) Modules, Joshua Dulcich
Honors Theses
Machine learning is obscure and expensive to develop. Neural architecture search (NAS) algorithms automate this process by learning to create premier ML networks, minimizing the bias and necessity of human experts. From this recently emerging field, most research has focused on optimizing a promisingly unique combination of NAS’s three segments. Despite regularly acquiring state of the art results, this practice sacrifices computing time and resources for slight increases in accuracy; this also obstructs performance comparison across papers. To resolve this issue, we use NASLib’s modular library to test the efficiency per module in a unique subset of combinations. Each NAS …
The Exploration And Analysis Of Mancala From An Ai Perspective, Trevon J. Hunter
The Exploration And Analysis Of Mancala From An Ai Perspective, Trevon J. Hunter
Honors Theses
Through the study of popular games such as Chess and Go, countless artificial intelligence (AI) research has been conducted in an attempt to create algorithms equipped for adversarial search problems. However, there are still a plethora of avenues that offer insight into further development. Mancala is traditionally a two-player board game that originated in the East and offers a unique opponent-based playing experience. This thesis not only attempts to create a competitive AI algorithm for mancala games by analyzing the performance of several different algorithms on this classic board game, but it also attempts to extract applications that may have …
Finding Optimal Input Parameters For Bayeswave, Kelsey M. Rook
Finding Optimal Input Parameters For Bayeswave, Kelsey M. Rook
Honors Theses
This project involves data analysis for LIGO with the goal of finding optimal input parameters for the BayesWave analysis pipeline, which is an algorithm for the detection of unmodelled gravitational wave transients. To test the BayesWave pipeline, we add binary black hole gravitational waveforms to LIGO noise, and run BayesWave with different combinations of parameters on the resulting signal data to find the best method of separating gravitational waves from noise and glitches. From the results, we calculate various statistical measures for each parameter combination in order to determine which allows for the most accurate classification of gravitational wave transients.
Assessing The Mean Neuronal Firing Rate Information Hypothesis Via Mutual Information, Greg W. Zdor
Assessing The Mean Neuronal Firing Rate Information Hypothesis Via Mutual Information, Greg W. Zdor
Honors Theses
While it is currently well accepted that the mean neuronal firing rate (MNFR) is a key parameter encoding information about sensory and motor events, in some cases the measured information due to MNFR is not adequate to explain the total neuron signal information content. In this study, several auditory neuron responses and corresponding MNFR--generated surrogates are analyzed using mutual information (MI) as a metric of information content. Results showed that for particular inter-spike gaps (ISG), data MI exceeded two standard deviations of the surrogate MNFR MI, indicating spike spacing and order also encode information.
Crawling Tor's Hidden Services And Depicting Their Interconnectivity, John-Luke N. Navarro
Crawling Tor's Hidden Services And Depicting Their Interconnectivity, John-Luke N. Navarro
Honors Theses
The Tor network is a popular online privacy platform that enables anonymous browsing, but is also notorious for the vast number of illicit marketplaces, goods and services available to users. Tor's protocols also secure hosted websites, known as hidden services, against unwanted tracking and location. Tor has attracted the attention of law enforcement agencies, who are interested in hidden service data analysis. However, little large-scale analysis is currently performed. To help address this issue, I constructed two tools. A specialized web crawler downloads bulk page-content from Tor's hidden services. This program crawls the Tor Network broadly, securely, and with more …
Adapting Architectural Models For Visualization Using Virtual Reality Headsets, Bernardo Martinez
Adapting Architectural Models For Visualization Using Virtual Reality Headsets, Bernardo Martinez
Honors Theses
Business contracts represent a main source of income for Architects. Acquiring these contracts requires the latest and most immersive technology that improves their sales against competitors. Virtual reality provides an in-depth experience that allows clients to have a reasonable assurance that the building meets their physical expectations. Videos and photos are detached and mundane; while they provide some visual representation they will not allow the user to compare his physical characteristics (height, length, width) with a 3D model. In this paper, I describe a procedure for automatically importing 3D models from Revit into Unreal4. I also describe the workflow required …