Within the past several years the technology of high-throughput sequencing has transformed the study of biology by offering unprecedented access to life's fundamental building block, DNA. With this transformation's potential a host of brand-new challenges have emerged, many of which lend themselves to being solved through computational methods. From de...
In this work, we study network coding technique, its relation to random matrices, and their applications to communication systems. The dissertation consists of three main contributions. First, we propose efficient algorithms for data synchronization via a broadcast channel using random network coding. Second, we study the resiliency of network coding...
Magnetic thin films have potential to improve devices such as on-chip inductors, and enable new technologies such as magnetic random access memory (MRAM).
The use of magnetic cores in on-chip inductors is typically limited to applications well under 1 GHz. At higher frequencies, the performance of the magnetic core is...
Incremental ADCs (IADCs) have found wide applications in sensor interface circuitry since, compared to ∆Σ ADCs, they provide low-latency high-accuracy conversion and easy multiplexing among multiple channels. On the other hand, continuous-time ∆Σ ADCs (CTDSM) have been receiving more and more attention as a power-efficient solution in targeting medium to...
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...
This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
Crowdsourcing is a popular paradigm to address the high demands for labeled data in big data deluge. It aims to produce accurate labels by effectively integrating noisy, non-expert labeling from crowdsourced workers (annotators). The machine learning community has been studying effective crowdsourcing methods for many years, and many models and...
The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...
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...