Search Constraints

Start Over
Filtering by: Creator Chang, Ping-Yu Remove constraint Creator: Chang, Ping-Yu Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Efficient Oblivious Access to Trees

    Creator:
    Hackebeil, Gabriel A.
    Abstract:
    The outsourcing of data storage and related infrastructure to third-party services in the cloud is a trend that has gained considerable momentum in the last decade due to the savings it affords companies in both capital and operational costs. Although encryption can alleviate some of the privacy concerns associated with...
    Resource Type:
    Masters Thesis

  • Visual object discovery and understanding

    Creator:
    Yuan, Jialin
    Abstract:
    Learning to recognize objects is a fundamental and essential step in human perception and understanding of the world. Accordingly, research of object discovery across diverse modalities plays a pivotal role in the context of computer vision. This field not only contributes significantly to enhancing our understanding of visual information but...
    Resource Type:
    Dissertation
    Full Text:
    -workers during the internships: Jingchen Liu, Yuh-jie Chen, Ye Yu, Gaurav Mittal, and Mei Chen. They kept

  • Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization

    Creator:
    Khorram, Saeed
    Abstract:
    In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...
    Resource Type:
    Masters Thesis

  • QuestWriter : a toolset for web-based Instruction

    Creator:
    Uppala, Srikanth
    Abstract:
    The potential of the Internet-especially, the World Wide Web- as a medium for instruction has been realized. Numerous web-based courses have been de­veloped in the recent past. However, most of these courses are nothing but glorified texts. The reasons being (a) lack of understanding of the pedagogic challenges of web-based...
    Resource Type:
    Capstone Project
    Full Text:
    comprehension. Say there are 6 students in a class (Anand, Bob, Chang, Divya, Eliza, and Farah). If Eliza

  • Identifying and Removing On-chip Network Bottleneck in Throughput Processors

    Creator:
    Li, Yunfan
    Abstract:
    The high level of parallelism in throughput processors such as GPGPUs has resulted in significantly changed on-chip data traffic behaviors. This demands new research to identify and address the limiting factors of networks-on-chip (NoCs) in the context of throughput processors. In this work, we first quantitatively analyze the performance of...
    Resource Type:
    Masters Thesis

  • Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

    Creator:
    Wang, Xinyao
    Abstract:
    Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
    Resource Type:
    Masters Thesis

  • Machine Learning Methods for Computational Sustainability

    Creator:
    Liu, Liping
    Abstract:
    Maintaining the sustainability of the earth’s ecosystems has attracted much attention as these ecosystems are facing more and more pressure from human activities. Machine learning can play an important role in promoting sustainability as a large amount of data is being collected from ecosystems. There are at least three important...
    Resource Type:
    Dissertation
    Full Text:
    Conditional Multinomial Mixture Model for Superset Label Learning Li-Ping Liu, Thomas G. Dietterich

  • Learning with Partial Supervision for Clustering and Classification

    Creator:
    Pei, Yuanli
    Abstract:
    In the field of machine learning, clustering and classification are two fundamental tasks. Traditionally, clustering is an unsupervised method, where no supervision about the data is available for learning; classification is a supervised task, where fully-labeled data are collected for training a classifier. In some scenarios, however, we may not...
    Resource Type:
    Dissertation
    Full Text:
    need. I especially thank my husband, Li-Ping Liu, for his love, support and unfailing advice. Finally

  • Learning with Limited Labeled Data in Natural Language Processing

    Creator:
    Obeidat, Rasha
    Abstract:
    The advent of deep learning models leads to a substantial improvement in a wide range of NLP tasks, achieving state-of-art performances without any hand-crafted features. However, training deep models requires a massive amount of labeled data. Labeling new data as a new task or domain emerges consumes time and efforts...
    Resource Type:
    Dissertation

  • Novelty Detection Under the Multi-Instance Multi-Label Framework

    Creator:
    Lou, Qi
    Abstract:
    Novelty detection plays an important role in machine learning and signal processing. This project studies novelty detection in a new setting where the data object is represented as a bag of instances and associated with multiple class labels, referred to as multi-instance multi-label (MIML) learning. Contrary to the common assumption...
    Resource Type:
    Capstone Project
    Full Text:
    Zhou, Min-Ling Zhang, Sheng-Jun Huang, and Yu-Feng Li, “Multi-instance multi-label learning,” Artif