Current Search:   Shorten, Connor (x)

View All Items

  • CSV Spreadsheet
(1 - 3 of 3)
Software Engineering: Social Impact and Perception
Title
Software Engineering: Social Impact and Perception.
Creator
Cardenas, Erika, Shorten, Connor, Escaleras, Monica
Abstract/Description
New software technologies are rapidly changing the economy. These changes have presented problems such as job displacement, high barrier to entry, and a gender gap in the engineering communities. In order to see the views of Americans regarding the challenges of software technologies, we conducted an online survey, gathering 500 responses. In recent news stories, it has been shown that there is a gender gap in the tech industry, but the women that participated in our survey are interested in...
Show moreNew software technologies are rapidly changing the economy. These changes have presented problems such as job displacement, high barrier to entry, and a gender gap in the engineering communities. In order to see the views of Americans regarding the challenges of software technologies, we conducted an online survey, gathering 500 responses. In recent news stories, it has been shown that there is a gender gap in the tech industry, but the women that participated in our survey are interested in learning software engineering as much as men. Additionally, our research found that younger people are not only required to use software tools more frequently but are the most interested in learning how to build them.  Finally, we found that a majority of people do not have any experience developing software. Our survey highlights some of the challenges of software technologies in the economy.
Show less
Date Issued
2018
PURL
http://purl.flvc.org/fau/fd/FAU_SR00000030
Subject Headings
College students --Research --United States.
Format
Document (PDF)
DATA AUGMENTATION IN DEEP LEARNING
Title
DATA AUGMENTATION IN DEEP LEARNING.
Creator
Shorten, Connor, Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description
Recent successes of Deep Learning-powered AI are largely due to the trio of: algorithms, GPU computing, and big data. Data could take the shape of hospital records, satellite images, or the text in this paragraph. Deep Learning algorithms typically need massive collections of data before they can make reliable predictions. This limitation inspired investigation into a class of techniques referred to as Data Augmentation. Data Augmentation was originally developed as a set of label-preserving...
Show moreRecent successes of Deep Learning-powered AI are largely due to the trio of: algorithms, GPU computing, and big data. Data could take the shape of hospital records, satellite images, or the text in this paragraph. Deep Learning algorithms typically need massive collections of data before they can make reliable predictions. This limitation inspired investigation into a class of techniques referred to as Data Augmentation. Data Augmentation was originally developed as a set of label-preserving transformations used in order to simulate large datasets from small ones. For example, imagine developing a classifier that categorizes images as either a “cat” or a “dog”. After initial collection and labeling, there may only be 500 of these images, which are not enough data points to train a Deep Learning model. By transforming these images with Data Augmentations such as rotations and brightness modifications, more labeled images are available for model training and classification! In addition to applications for learning from limited labeled data, Data Augmentation can also be used for generalization testing. For example, we can augment the test set to set the visual style of images to “winter” and see how that impacts the performance of a stop sign detector. The dissertation begins with an overview of Deep Learning methods such as neural network architectures, gradient descent optimization, and generalization testing. Following an initial description of this technology, the dissertation explains overfitting. Overfitting is the crux of Deep Learning methods in which improvements to the training set do not lead to improvements on the testing set. To the rescue are Data Augmentation techniques, of which the Dissertation presents an overview of the augmentations used for both image and text data, as well as the promising potential of generative data augmentation with models such as ChatGPT. The dissertation then describes three major experimental works revolving around CIFAR-10 image classification, language modeling a novel dataset of Keras information, and patient survival classification from COVID-19 Electronic Health Records. The dissertation concludes with a reflection on the evolution of limitations of Deep Learning and directions for future work.
Show less
Date Issued
2023
PURL
http://purl.flvc.org/fau/fd/FA00014228
Subject Headings
Deep learning (Machine learning), Artificial intelligence, Data augmentation
Format
Document (PDF)
An Exploration into Synthetic Data and Generative Aversarial Networks
Title
An Exploration into Synthetic Data and Generative Aversarial Networks.
Creator
Shorten, Connor M., Khoshgoftaar, Taghi M., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description
This Thesis surveys the landscape of Data Augmentation for image datasets. Completing this survey inspired further study into a method of generative modeling known as Generative Adversarial Networks (GANs). A survey on GANs was conducted to understood recent developments and the problems related to training them. Following this survey, four experiments were proposed to test the application of GANs for data augmentation and to contribute to the quality improvement in GAN-generated data....
Show moreThis Thesis surveys the landscape of Data Augmentation for image datasets. Completing this survey inspired further study into a method of generative modeling known as Generative Adversarial Networks (GANs). A survey on GANs was conducted to understood recent developments and the problems related to training them. Following this survey, four experiments were proposed to test the application of GANs for data augmentation and to contribute to the quality improvement in GAN-generated data. Experimental results demonstrate the effectiveness of GAN-generated data as a pre-training metric. The other experiments discuss important characteristics of GAN models such as the refining of prior information, transferring generative models from large datasets to small data, and automating the design of Deep Neural Networks within the context of the GAN framework. This Thesis will provide readers with a complete introduction to Data Augmentation and Generative Adversarial Networks, as well as insights into the future of these techniques.
Show less
Date Issued
2019
PURL
http://purl.flvc.org/fau/fd/FA00013263
Subject Headings
Neural networks (Computer science), Computer vision, Images, Generative adversarial networks, Data sets
Format
Document (PDF)