A core problem in many computer vision applications is visual recognition (including object classification, detection and localization). Recent advances in artificial neural networks (aka ”deep learning”) have significantly pushed forward the state-of-the-art visual recognition performances. However, due to the lack of semantic structure modeling, most current deep learning approaches do...
Modeling human language is at the very frontier of machine learning and artificial intelligence. Statistical language models are probabilistic models that assign probabilities to sequences of words. For example, topic models are frequently used text-mining tools to organize a vast set of unstructured documents by exploring their theme structure. More...
Blockchains are an exciting new type of Peer-to-Peer (P2P) distributed systems, which enable parties to transact directly, and maintain the record of said interactions in a distributed manner. A unique feature of blockchains is their ability to maintain a consensus without requiring knowledge on the number of participants, nor their...
The theory of how humans and machines control and communicate with each other is at the core of the scientific field known as Human-Robot Interaction (HRI). Researchers in this sub-discipline of robotics are therefore particularly interested in developing methods to chuppahreduce the inherent friction in this communication and control channel....
This dissertation combines perspectives from social networks and teams research to advance understanding of team self-assembly. Across three substantive chapters, I explore team member search behaviors and invitation patterns in contexts where individuals exercise agency to select team members. First, I consider the search for team members in a social...
Abstract The work presented in this dissertation addresses three broad areas of video signal processing: video transmission, motion estimation and error concealment. In the first category, focused on the source-side, we present two machine learning models for efficient content-aware resource allocation and packet prioritization for video transmission over shared/constrained, lossy...
Annual age-adjusted breast cancer incidence rates in the United States have been static for decades. More recently, the development of massively parallel, high throughput DNA sequencing has enabled the cataloging of somatic mutations in cancer. Mutations are non-random and occur within sequence motifs. These motifs provide us with evidence to...
Recovering three-dimensional (3D) structural information of a specimen from a single two-dimensional (2D) measurement remains an important but challenging task in microscopic imaging. A conventional 2D microscopic image has a shallow depth-of-focus (DoF). Thus, recovering 3D information usually requires sequentially z-scanning the focal planes. This process is time consuming and...
Automated sketch collaborators might help us create more dynamic intelligent tutoring systems, work out designs, reduce bias in solving spatial social problems, and organize our ideas. Here, we examine some properties of sketch recognition methods designed to help serve that goal. Structure Mapping techniques are applied to symbolic structural descriptions...
Natural Language Processing methods have become increasingly important for a variety of high- and low-level tasks including speech recognition, question answering, and automatic language translation. The state of the art performance of these methods is continuously advancing, but reliance on labeled training data sets often creates an artificial upper bound...