Digital Commons Network^™

Comparing Learned Representations Between Unpruned And Pruned Deep Convolutional Neural Networks, Parker Mitchell

Master's Theses

While deep neural networks have shown impressive performance in computer vision tasks, natural language processing, and other domains, the sizes and inference times of these models can often prevent them from being used on resource-constrained systems. Furthermore, as these networks grow larger in size and complexity, it can become even harder to understand the learned representations of the input data that these networks form through training. These issues of growing network size, increasing complexity and runtime, and ambiguity in the understanding of internal representations serve as guiding points for this work.

In this thesis, we create a neural network that …

Legislative Language For Success, Sanjana Gundala

Master's Theses

Legislative committee meetings are an integral part of the lawmaking process for local and state bills. The testimony presented during these meetings is a large factor in the outcome of the proposed bill. This research uses Natural Language Processing and Machine Learning techniques to analyze testimonies from California Legislative committee meetings from 2015-2016 in order to identify what aspects of a testimony makes it successful. A testimony is considered successful if the alignment of the testimony matches the bill outcome (alignment is "For" and the bill passes or alignment is "Against" and the bill fails). The process of finding what …

A Survey Of Computer Graphics Facial Animation Methods: Comparing Traditional Approaches To Machine Learning Methods, Joseph A. Johnson

Master's Theses

Human communications rely on facial expression to denote mood, sentiment, and intent. Realistic facial animation of computer graphic models of human faces can be difficult to achieve as a result of the many details that must be approximated in generating believable facial expressions. Many theoretical approaches have been researched and implemented to create more and more accurate animations that can effectively portray human emotions. Even though many of these approaches are able to generate realistic looking expressions, they typically require a lot of artistic intervention to achieve a believable result. To reduce the intervention needed to create realistic facial animation, …

Improving Swarm Performance By Applying Machine Learning To A New Dynamic Survey, John Taylor Jackson

Master's Theses

A company, Unanimous AI, has created a software platform that allows individuals to come together as a group or a human swarm to make decisions. These human swarms amplify the decision-making capabilities of both the individuals and the group. One way Unanimous AI increases the swarm’s collective decision-making capabilities is by limiting the swarm to more informed individuals on the given topic. The previous way Unanimous AI selected users to enter the swarm was improved upon by a new methodology that is detailed in this study. This new methodology implements a new type of survey that collects data that is …

Detecting Speakers In Video Footage, Michael Williams

Master's Theses

Facial recognition is a powerful tool for identifying people visually. Yet, when the end goal is more specific than merely identifying the person in a picture problems can arise. Speaker identification is one such task which expects more predictive power out of a facial recognition system than can be provided on its own. Speaker identification is the task of identifying who is speaking in video not simply who is present in the video. This extra requirement introduces numerous false positives into the facial recognition system largely due to one main scenario. The person speaking is not on camera. This paper …