Refining learning models in grammatical inference by Wang, Xiangrui

“…We introduce the use of recurrent neural networks (RNNs) and present a pruning learning method to avoid the exponential space costs. …”
Get full text

Machine learning for chemical components testing by Tan, Ashley Zhao Kiat

“…Following this, two new machine learning approaches are taken to evaluate the effectiveness on chemical mixture identification. …”
Get full text

15.093 / 2.098 Optimization Methods (SMA 5213), Fall 2004 by Bertsimas, Dimitris

Get full text

Incremental learning technologies for semantic segmentation by Yang, Yizhuo

“…To solve this problem, an incremental learning method: Combination of Old Prediction and Modified Label (COPML) is developed in this dissertation project. …”
Get full text

Modeling e-learning effectiveness and usability by Leong, Lock Wah.

“…The Kirkpatrick model and the Usability method are combined into questionnaire to obtain feedback from users after their E-Learning training. …”
Get full text

Imbalanced data learning for biomedical application by Xie, Vincent JianHan.

“…This report explores a method of imbalance data learning, investigating the use of HRV parameters and vital signs as predictor of cardiac arrest occurring 72 hours within hospital admission. …”
Get full text

Machine learning based cybersecurity analytics by Tang, Yan Shuo

“…Most of the important information in packet are used to form NetFlow to act as an enhancement for packets. Machine Learning (Ensemble Method – XGBoost) is created for detecting such data exfiltration. …”
Get full text

Privacy-preserving graph representation learning by Lan, Xin

“…There are several disciplines in which graph representation learning is used. Graph neural networks in particular, as a novel kind of link prediction method, can extract hidden link information from accessible network data in the field of link prediction. …”
Get full text

Learning segmentation from point trajectories by Karazija, L, Laina, I, Rupprecht, C, Vedaldi, A

Deep learning for multiple object tracking by Gao, Junjie

“…My work combines this traditional strategy with the idea of metric learning together to ensure the robustness of trained identity information.…”
Get full text

Joint Feature Learning for Face Recognition by Lu, Jiwen, Liong, Venice Erin, Wang, Gang, Moulin, Pierre

“…Unlike many existing face recognition systems, where conventional feature descriptors, such as local binary patterns and Gabor features, are used for face representation, we propose an unsupervised feature learning method to learn hierarchical feature representation. …”
Get full text
Get full text

Deep learning based action recognition by Ong, Zong You

“…One of the more successful ways of recognizing human action is through the use of skeleton data. This method provides an excellent representation for describing human activities. …”
Get full text

Software development for E-learning tool by Foong, Alexander Kwok Leong

“…Therefore, these apps are expensive for students to learn with. Furthermore, existing knowledge of FEM is required for these apps, making it hard for students to apprehend. …”
Get full text

Predictive maintenance using machine learning by Amal Roy Lerroy Ashwin

“…An ensemble of AEs was implemented with ensemble learning to further improve the performance of anomaly detection. …”
Get full text

Comparison of character recognition performance - bayes classifier and neural network methods by Low, Siew Eng.

“…In this project, two learning schemes had been tested and verified, in the recognition unit within the image processing environment of the Machine Vision Tool, namely the Bayes classifier method and the neural network-error back propagation gradient descent learning method. …”
Get full text

Investigating hybrid methods of fabricating formamidinium-based perovskite solar cells by Krishnan, Sriniketh

“…Although solution processing is the most popular and successful method to fabricate perovskites, it is limited by its scalability and use of toxic solvents. …”
Get full text

Elucidating the mechanism of mRNA transport using novel imaging technologies by Stoychev, D

“…I begin to fill this technological gap by assessing and applying state-of-the-art methods from the fields of microscopy and image processing. …”

Numerical and Analytical Methods in Low-Dimensional Strongly Correlated Quantum Systems by Peng, Changnan

“…The study of low-dimensional strongly correlated quantum systems lies at the intersection of intricate theoretical models and practical numerical methods, offering deep insights into condensed matter physics. …”
Get full text

A Mixed-Methods Research Design to Advance Inclusive and Equitable Teaching by Soicher, Raechel N., Baker, Amanda R., Thomas, Ruthann C.

“…We developed an innovative framework and mixed methods research design to systematically assess inclusive and equitable teaching at the student, course, department, and institution levels. …”
Get full text

Determination of soil-water characteristics curves of sands using the evaporation method by On, Roger Zhi Wei

“…Commercial equipment such as the HYPROP 2 by Meter Group AG has been developed to expedite the experimental process of obtaining the SWCC of soils from 0 to 200 kPa suction using the evaporation method but is very costly. Moreover, such commercial equipment requires a steep learning curve and proper training to use them effectively. …”
Get full text