Search
Skip to Search Results- 2Abdi Oskouie, Mina
- 2Birkbeck, Neil Aylon Charles
- 2Cai, Zhipeng
- 2Chen, Jiyang
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 74Machine Learning
- 70Reinforcement Learning
- 41Artificial Intelligence
- 36Machine learning
- 22Natural Language Processing
- 22Reinforcement learning
-
Exploring Chinese Learners’ of English Response to Negative Language Transfer Feedback: An Evaluation of a Writing Assistant Tool
DownloadFall 2023
Previous research has enhanced our understanding of feedback from peers, teachers, and software as well as the widely reported negative language transfer phenomenon. However, the impact of an automated writing assistant tool that specifically provides negative language transfer feedback on...
-
Exploring Methods for Generating and Evaluating Skill Targeted Reading Comprehension Questions
DownloadSpring 2024
It takes skilled teachers a significant amount of time and effort to create high quality reading comprehension questions, often making it impractical to target a particular reader’s weaknesses. Recently, language models have been proposed as a tool to help teachers fill this gap, allowing these...
-
Fall 2022
Overfitting is a phenomenon when a machine learning system learns the patterns in training data so well that it starts to inauspiciously affect the model performance on unseen data. In practice, machine learning systems that overfit are not deployable rather systems that generalize well and do...
-
Exploring Surprisal from Various Language Models for Predicting English Reading Times of People with Different Language Backgrounds
DownloadFall 2023
Surprisal estimated by language models is predictive of reading time in first-language (L1) reading. Research is emerging to determine whether this observation extends to reading in a second language (L2). Current attempts to characterize differences in the predictive power of surprisal for L1...
-
Fall 2011
Pointer analysis is a program analysis that determines the memory locations pointed to by individual pointers. Imprecise pointer information is a major impediment to data-flow analyses and back-end optimizations that depend on pointer information. Most pointer analyses are based on a points-to...
-
Extending Differentiable Programming to include Non-differentiable Modules using Differentiable Bypass for Combining Convolutional Neural Networks and Dynamic Programming into an End-to-end Trainable Framework
DownloadSpring 2019
Differentiable Programming is the paradigm where different functions or modules are combined into a unified pipeline with the purpose of applying end-to-end learning or optimization. A natural impediment is the non-differentiability characteristic of many modules. This thesis proposes a new way...
-
Spring 2020
The web contains a large volume of tables that provide structured information about entities and relationships. This data may be used as a source for exploratory searches and to gather information about desired entities. This thesis focuses on one particular exploratory search where given a query...
-
Fall 2009
In this thesis, we propose mechanisms to extend the lifetime of wireless sensor networks. In-network data aggregation is considered on both tree-based and flow-based routing protocols during the process of data collection to reduce redundant transmissions. In the flow-based data collection...
-
Extending the Sliding-step Technique of Stochastic Gradient Descent to Temporal Difference Learning
DownloadFall 2018
Stochastic gradient descent is at the heart of many recent advances in machine learning. In each of a series of steps, stochastic gradient descent processes an example and adjusts the weight vector in the direction that would most reduce the error for that example. A step-size parameter is used...