Search Constraints

Start Over
Filtering by: Creator Hernandez, Jose Remove constraint Creator: Hernandez, Jose Academic Affiliation Electrical Engineering and Computer Science Remove constraint Academic Affiliation: Electrical Engineering and Computer Science

Search Results

  • Representationally Robust and Scalable Learning over Relational Databases

    Creator:
    Picado Leiva, Jose Manuel
    Abstract:
    Learning novel concepts from relational databases is an important problem with applications in several disciplines, such as data management, natural language processing, and bioinformatics. For a learning algorithm to be effective, the input data should be clean and in some desired representation. However, real-world data is usually heterogeneous – the...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Jose Manuel Picado Leiva

  • Relational Learning over Dirty Data Using Data Constraints

    Creator:
    Lee, Ga Young
    Abstract:
    Real-world datasets are dirty and contain many errors. Examples of these issues are violations of integrity constraints, duplicates, and inconsistencies in representing data values and entities. Applying machine learning on dirty databases may lead to inaccurate results. Users have to spend a lot of time and effort repairing data errors...
    Resource Type:
    Masters Thesis
    Full Text:
    Termehchy primarily led this research project as an extension of Dr. Jose Picado’s thesis. Jack Davis and I

  • Model Selection of Discrete Classifiers under Class and Cost Distribution Change: An Empirical Study

    Creator:
    Ahmed, Nahian and Hutchinson, Rebecca A.
    Abstract:
    A variety of important machine learning applications require predictions on test data with different characteristics than the data on which a model was trained and validated. In particular, test data may have a different relative frequency of positives and negatives (i.e., class distribution) and/or different mislabeling costs of false positive...
    Resource Type:
    Technical Report
    Full Text:
    . Model selection as a threshold choice problem based on expected loss/cost has been studied by Hernández

  • A comparative study of lowpass continuous-time delta-sigma modulators with pulse-shaped DACs

    Creator:
    Fang, Jie
    Abstract:
    Recently, continuous-time ΔΣ modulators are appearing increasingly often in both the literature and the marketplace due to their features of inherent antialiasing and relaxed requirements for opamp and so on. However, several nonideal factors such as clock jitter, excess loop delay, inter-symbol interference and so on, degrade the SNR performance...
    Resource Type:
    Masters Thesis
    Full Text:
    Meng, Zhengyong Zhang, Xuefeng Chen, Jose Ceballos, Chenwei Zhang, Yoshio Nishida and so on. I extend

  • Uncertainty in Deep Learning with Implicit Neural Networks

    Creator:
    Ratzlaff, Neale
    Abstract:
    The ability to extract uncertainties from predictions is crucial for the adoption of deep learning systems to safety-critical applications. Uncertainty estimates can be used as a failure signal, which is necessary for automating complex tasks where safety is a concern. Furthermore, current deep learning systems do not provide uncertainty estimates,...
    Resource Type:
    Dissertation
    Full Text:
    parameters. Probabilistic Backprop- agation [Hernández-Lobato and Adams, 2015] makes use of the

  • A wideband low-power continuous-time delta-sigma modulator for next generation wireless applications

    Creator:
    Chen, Xuefeng
    Abstract:
    Delta-Sigma (ΔΣ) analog-to-digital converters (ADCs) are widely used in wireless transceivers. Recently, continuous-time (CT) ΔΣ ADCs gain growing interest in wireless applications for their lower power consumption and wider input bandwidth as compared with the discrete-time (DT) counterparts. In this thesis, a wideband low-power CT ΔΣ modulator for next generation...
    Resource Type:
    Dissertation
    Full Text:
    generous and thoughtful help from Jipeng Li and Xuesheng Wang. It was Jose Silva who helped me a lot to

  • Novel approaches to promoting end-user programming

    Creator:
    Bahmani, Faezeh
    Abstract:
    End-user programming has become widespread. The increasing size of this population and the prevalence of barriers that they face has sparked the development of approaches that promote end-user programing by helping them overcome barriers and teaching them programming. Despite the fact that these approaches have done well in achieving those...
    Resource Type:
    Masters Thesis
    Full Text:
    Visual Languages and Human-Centric Computing (VL/HCC), San Jose, CA, USA 3

  • Low-power double-sampled delta-sigma modulator for broadband applications

    Creator:
    Shen, Weilun
    Abstract:
    High speed and high resolution analog-to-digital converter is a key building block for broadband wireless communications, high definition video applications, medical images and so on. By leveraging the down scaling of the latest CMOS technology and the noise shaping properties, delta-sigma (ΔΣ) ADCs are able to achieve wide-band operation and...
    Resource Type:
    Dissertation
    Full Text:
    of in academia. It is at Broadcom analog group, San Jose where I learned that kind of fashion to do

  • Power Efficient Architectures for High Accuracy Analog-to-Digital Converters

    Creator:
    Zhang, Yi
    Abstract:
    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...
    Resource Type:
    Dissertation

  • Methods for Detection and Recovery of Out-of-Distribution Examples

    Creator:
    Ratzlaff, Neale J.
    Abstract:
    Deep neural networks currently comprise the backbone of many applications where safety is a critical concern, for example: autonomous driving and medical diagnostics. Unfortunately these systems currently fail to detect out-of-distribution (OOD) inputs and can be prone to making dangerous errors when exposed to them. In addition, these same systems...
    Resource Type:
    Masters Thesis