Search
Now showing items 41-50 of 107
Representing Networks: Centrality, Node Embeddings, Community Outliers and Graph Representation
Networks are ubiquitous. We start our technical work in this thesis by exploring the classical concept of node centrality (also known as influence measure) in information networks. Like clustering, node centrality is also ...
Embedding Networks: Node and Graph Level Representations
Graph neural networks gained significant attention for graph representation and classification in the machine learning community. For graph classification, different pooling techniques are introduced, but none of them has ...
Kernel-Based Image Filtering: Fast Algorithms and Applications
Image filtering is a fundamental preprocessing task in computer vision and image processing.
Various linear and nonlinear filters are routinely used for enhancement, upsampling, sharpening,
reconstruction, etc. The focus ...
Devanagari Online Handwritten Character Recognition
In this thesis, a classifier based on local sub-unit level and global character level representations
of a character, using stroke direction and order variations independent features, is developed
for recognition of ...
On Learning and Lower Bound Problems Related to the Iterated Matrix Multiplication Polynomial
The iterated matrix multiplication polynomial (IMM) of width w and length d is the 1x1 entry in the product of d square matrices of size w. The w^2d entries in the d matrices are distinct variables. In this thesis, we study ...
Algorithms for Social Good in Online Platforms with Guarantees on Honest Participation and Fairness
Recent decades have seen a revolution in the way people communicate, buy products, learn new things, and share life experiences. This has spurred the growth of online platforms that enable users from all over the globe to ...
Verification of a Generative Separation Kernel
A Separation Kernel is a small specialized microkernel that provides a sand-boxed execution environment
for a given set of processes (also called \subjects"). The subjects may communicate
only via declared memory channels, ...
Deep Learning Models for Few-shot and Metric Learning
Deep neural network-based models have achieved unprecedented performance levels over many tasks in the traditional supervised setting and scale well with large quantities of data. On the other hand, improving performance ...
Deep Learning for Bug Localization and Program Repair
In this thesis, we focus on the problem of program debugging and present novel deep learning
based techniques for bug-localization and program repair. Deep learning techniques have been
successfully applied to a variety ...
Fully Resilient Non-Interactive ID-Based Hierarchical Key Agreement
Non-Interactive Key Agreement (NIKA) is a cryptographic primitive which allows two parties
to agree on a shared secret key without any interaction. Identity-based Non-Interactive Key
Agreement (ID-NIKA) allows each party ...