The Façade photometric modeling system, developed by Paul E Debevec at Berkley, is capable of transforming a sparse set of camera images of an architectural scene into a photorealistic 3D model. Users define a rough model out of primitive building blocks and mark where a portion of the edges of...
Global Positioning Systems have allowed for precise timing of power system measurements over wide areas. This newly found capability has the potential to provide much greater insight into the operation of the power system and its response to contingencies, but few analytical techniques currently exist that provide enough robustness and...
Digital libraries are digitally accessible, organized collections of knowledge. Although under this broad definition any digitally accessible data set might be considered a digital library, the term is generally reserved for collections whose structures are carefully documented and made available in the form of so-called metadata. There is no specific...
GEM-GIS is a prototype of a web-based GIS/Database application for managing a germplasm collection. This application include a database, a map interface, a set of web forms for database access, and an analysis module. The analysis module perform statistical analysis for the accessions of a species selected by the user...
The core element of democracy is elections. Modern elections not only cost a lot of money to conduct elections, but we also bear a lot of social costs when the election is questioned. For this reason, the US and European countries have been considering ways to innovate by introducing IT...
RNAs play important roles in multiple cellular processes, and many of their functions rely on folding to specific structures. To maintain their functions, secondary structures of RNA homologs are conserved across evolution. These conserved structures provide critical targets for diagnostics and therapeutics. Thus, there is a need for developing fast...
Ring Amplifier serves as a great candidate both for precision amplification and fast integration in the discrete time system. It can be utilized in high-performance analog-to-digital converters (ADCs). In high-speed ADC utilizing pipelined architectures with residue amplification, Successive-Approximation Register (SAR) ADCs as the sub-ADC and power efficient Ring Amplifier based...
Recent advances in computing, communication, and artificial intelligence (AI) technologies have made our world more interconnected and data-rich than ever with the proliferation of smart devices and sensors. As a result, we are increasingly dependent on electronic devices and sensors to automate away life’s mundane parts. For example, in business...
Simultaneous speech translation (SimulST) is widely useful in many cross-lingual communication scenarios, including multinational conferences and international traveling. Since text-based simultaneous machine translation (SimulMT) has achieved great success in recent years. The conventional cascaded approach for SimulST uses a pipeline of streaming ASR followed by simultaneous MT but suffers from...
Alignment of genomic sequences from different species is becoming an increasingly powerful method in biology, and is being used for many purposes. The result of sequence alignments is a list of pairs of matched locations between the pattern string and the text string. However, without any proper visualization tools to...
Secure two-party computation (2PC) is the task of performing arbitrary calculations on secret inputs provided by two parties, while maintaining secrecy if at least one party is honest. 2PC has been applied to privacy-preserving record linkage and machine learning, in areas such as medicine where maintaining privacy is crucial. One...
Learning latent space representations of high-dimensional world states has been at the core of recent rapid growth in reinforcement learning(RL). At the same time, RL algo- rithms have suffered from ignored uncertainties in the predicted estimates of model-free or model-based methods. In our work, we investigate both of these aspects...
Iterative algorithms are simple yet efficient in solving large-scale optimization problems in practice. With a surge in the amount of data in past decades, these methods have become increasingly important in many application areas including matrix/tensor recovery, deep learning, data mining, and reinforcement learning. To optimize or improve iterative algorithms,...
In this thesis, a new learning algorithm is introduced that is targeted towards individual fairness. In order to be individually fair, mispredictions need to be avoided as each such prediction means the learning algorithm was unfair towards some individual. Therefore, achieving individual fairness implies having a perfect classifier, which is...
Machine common sense remains a broad, potentially unbounded problem in AI. Our focus is to move toward AI systems that can develop common-sense reasoning similar to humans to detect anomalies. In particular, we study the problem of detecting the violation of expectations when object appearance or motion dynamics change from...
Many home users nowadays use various smart devices to improve the efficiency and convenience of their home environments. Trigger-action platforms such as “If-This-Then-That” (IFTTT) enable end users to connect different smart devices and services using simple apps to control these devices and automate the tasks (e.g., if the camera detects...
Currently, a popular approach to image classification uses the deep Transformer architecture. In a Transformer, the attention mechanism enables the model to learn efficiently with fewer computational resources than the convolutional neural networks (CNNs). In this thesis, we study the sparse attention mechanism widely used in the Transformers developed specifically...
NAND flash based solid state drives (SSDs) require out-of-place updating due to the characteristics of flash memories. In addition, due to the mismatched granularity between read/write and erase operations, a cleaning policy involving garbage collection and wear leveling has to perform data migration incurring high overhead. Another challenge is that...
In standard training regimes, one assumes that the classes presented to a model constitute all of the classes that the model will encounter when it is deployed. In real deployment scenarios, however, a model can sometimes encounter situations or objects that it has never seen. When these scenarios are safety-critical,...