• Expert-Assisted Transfer Reinforcement Learning 

  Slack, Dylan (2019)

  Reinforcement Learning is concerned with developing machine learning approaches to answer the question: "What should I do?" Transfer Learning attempts to use previously trained Reinforcement Learning models to achieve ...
• A General Framework for Proving Sauer-Shelah Type Lemmas 

  Yutong, Li (2019)

  We present two versions of "shatter functions" and show that they are upper-bounded by the same polynomial, known as the Sauer-Shelah dichotomy. Then, we analyze a third setting due to Chase and Freitag [3], the $(n, ...
• The Ergonomics of Faceted Execution 

  Fisher, Ian (2019)

  This thesis reviews several challenges in the use and implementation of faceted execution, a programming-language mechanism for enforcing privacy policies. I present a proof-of-concept of a module-rewriting technique for ...
• History and Development of Reversible Architecture 

  Eguia, Ojani (2019)

  Reversible computing is the paradigm in which every computation is physically and easily reversible in an unambiguous way. For a reversible machine, this would apply to programs, gates, memory, and everything in between. ...
• Foundations and Applications of Authorship Attribution Analysis 

  Shukla, Rohan (2019)

  Authorship attribution is the process of identifying the author of a given work. This thesis surveys the history and foundations of authorship attribution, and then analyzes multiple machine learning methods that are used ...
• ANALYZING THE COMPAS ALGORITHM IN CRIMINAL DEFENDANT RISK ASSESSMENT 

  Ayad, Yasmine (2019)

  For my thesis, I analyzed the COMPAS recidivism prediction tool made by Equivant which aims to see how likely a defendant charged with a crime will re-offending given a score from 1-10 where 1 indicating lowest risk and ...
• Information Flow Control on the Web with Racets 

  Soulanille, Matthew (2019)

  Faceted execution is a technique for dynamic information flow control that allows programmers to program in a policy-agnostic manner. Racets uses macros to extend Racket with support for faceted execution. We present the ...
• Grapheme to Phoneme Conversion: Using Input Strictly Local Finite State Transducers 

  Morgan, Gregory M. (2019)

  This thesis explores the many methods of Grapheme to Phoneme Conversion (G2P) including dictionary look-up, rule-based approaches, and probabilistic approaches such as Joint Sequence Models (JSM), Recurrent Neural Networks ...
• How Acquiring the “Perfect Match” within Clothing Recommendation Systems Relies on Human Judgement: Literature Review 

  Quintero, Amanda-Lynn (2019)

  Recommendation systems exist in almost every aspect of online business. Whether the system is recommending books, movies, clothes, etc., an algorithm is running behind the scenes. These algorithms are hard to acquire in ...
• Scaling Faceted Execution in Racket using Languages as Libraries Approach 

  Parker, David (2019)

  Reasoning about information flow is essential when creating a secure system, and faceted execution is one way to ensure that data is only being accessed and modified by processes that have permission to do so. Faceted ...
• State Influence Calculations for Deep Q-Networks 

  Villalta, Christopher (2019)

  Machine learning has become a popular tool for decision making. As these algorithms continue to make more of our decisions, the question arises of whether they are sound and just. Seeking the answer to this question is a ...
• A Comparison of Fairness-Aware Machine Learning Algorithms 

  Roth, Derek (2018)

  Fairness, as it applies to algorithms, implies that the decisions made by an algorithm are being made such that there is no discrimination against individuals or groups in labeled data sets. In this paper, I give a summary ...
• Android Social Media Permissions: User interfaces to bridge expectation and reality 

  Alliyu, Oluwatosin (2018)

  Androids phones were first introduced late 2008 and has become increasingly popular today. While android phones became increasingly popular so did the Android applications market; not only are more and more people downloading ...
• Data Locality Practices of MapReduce and Spark: Efficiency and Effectiveness 

  Snow, Alex (2018)

  The parallel computing community has produced various cluster computing frameworks to process the immense amounts of data we generate in the modern age. Two in particular, Hadoop MapReduce and Spark, rose above the rest ...
• Scaling Up Abstract Interpretation by Abstracting Abstract Machines 

  Wan, Austin (2018)

  This paper examines the ideas presented in Van Horn and Might’s 2010 paper, Abstracting Abstract Machines as a recent development of static analysis of programs. The paper consolidates background information on the lambda ...
• COMPARATIVE ANALYSIS OF DISTRIBUTED METHODS FOR PAGERANK COMPUTATION 

  Weinstein, Noah (2018)

  The PageRank of a vector is a measure of centrality for nodes in a network. Three ways to calculate the PageRank are using power iteration, Monte Carlo methods, and iterative graph methods using Spark. The graph methods ...
• Plane and Simple: Characterizing and Testing Planarity 

  Emery, Dylan (2018)

  An exploration of previous work on planarity with a relatively simple and complete proof of Kuratowski's theorem and an in depth explanation of the foundations of the Left-Right Planarity algorithm.
• Speed up Three Dense Matrix Multiplications By Changing Iteration Order 

  Chen, Zongchang (2018)

  Improving the performance of dense numerical programs is an area that has been studied for decades. There are numerous approaches that people have applied on those problems, including upgrading the algorithm, running the ...
• Analyzing the Flow of Sensitive Data and Facebook Permissions in Android Applications 

  Ellenburg, Skyler (2018)

  When Android applications request permission to use certain data, the extent to which they use that data and where it goes is often vague, deceptive, or completely ignored by the user. Researchers in this field examine the ...
• Analyzing Iteration-Space Performance Tuning Using the Deriche Recursive Filtering Algorithm 

  Glaser, Mary (2018)

  No matter how efficient or satisfactory an algorithm or program may be, we as computer scientists are always looking to improve our programs by means of speeding them up or making them more accurate. In this paper, we will ...

View more