Search Constraints

Start Over
Filtering by: Creator Dunham, J. B. Remove constraint Creator: Dunham, J. B. Committee Member Fern, Alan Remove constraint Committee Member: Fern, Alan

Search Results

  • 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
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 B Appendix: Robust Neural Networks . . . . . . . . . . . . . . . . . . . . . . 53 LIST OF

  • Usable and Scalable Querying of Scientific Datasets

    Creator:
    McCamish, Benjamin J.
    Abstract:
    Scientists and engineers have to analyze and query multiple large databases. Analysis over databases created by phasor measurement units can provide insight into the health of the grid, thereby improving control over operations. Realizing this data-driven control, however, requires validating, processing and storing massive amounts of PMU data efficiently, which...
    Resource Type:
    Dissertation
    Full Text:
    system measurements Ben McCamish, Rich Meier, Jordan Landford, Robert B Bass, David Chiu, Eduardo

  • Deep Learning for Human and Biological Languages

    Creator:
    Hong, Junki
    Abstract:
    We explore the application of deep learning to the disparate fields of natural language processing and computational biology. Both the sentences uttered by humans as well as the RNA and protein sequences found within the cells of their bodies can be considered formal languages in computer science, as sets of...
    Resource Type:
    Dissertation
    Full Text:
    and then cube-pruning to attain linear O(n ·b log(b)) runtime complexity. Despite being an inex- act

  • Weakly Supervised Learning for Activity Recognition from Time Series Data

    Creator:
    Guan, Xinze
    Abstract:
    The thesis focuses on activity recognition from sensor data, which has spurred a great deal of interest due to its impact on health care and security. Previous work on activity recognition from multivariate time series data has mainly applied supervised learning techniques which require a high degree of annotation effort...
    Resource Type:
    Dissertation
    Full Text:
    the entry Aij represents the probability of transitioning from state i to state j. B is the emission

  • Domain-Independent Planning for Markov Decision Processes with Factored State and Action Spaces

    Creator:
    Raghavan, Aswin
    Abstract:
    Markov Decision Processes (MDPs) are the de-facto formalism for studying sequential decision making problems with uncertainty, ranging from classical problems such as inventory control and path planning, to more complex problems such as reservoir control under rainfall uncertainty and emergency response optimization for fire and medical emergencies. Most prior research...
    Resource Type:
    Dissertation
    Full Text:
    Improvement (V 0n+1, π)← T (Vn) if ||V 0n+1 − Vn|| ≤ �(1− γ)/2γ return (Vn, π) //Partial Policy Evaluation j

  • Planning in multi-agent partially observable domains using sparse sampling

    Creator:
    Donneau-Golencer, Thierry D.
    Abstract:
    A large number of sequential decision-making problems in uncertain environments can be modeled as Markov Decision Processes (MDPs). In such settings, an agent can observe at each time step the state of the environment and then executes an action, causing a stochastic transition to a new state of the environment...
    Resource Type:
    Masters Thesis
    Full Text:
    ^U�U � T�U � 1�/�/G�+/�@J<>�+HJ�?&2D.&J:;1�/�89<"�+-0/�-2:B<"���w*��98!��D"�+-2/�3[H_&2gc

  • Adaptive Movement Intent Decoding for Intuitive Control of Neuroprostheses

    Creator:
    George, Damon A.
    Abstract:
    Movement intent decoders, which interpret volitional movement intent from human bioelectric signals, can be incorporated into modern neuroprostheses to offer people living with limb loss or paralysis the potential to regain their lost motor control. Machine learning methods have become the research standard for continuous decoders with high degrees of...
    Resource Type:
    Masters Thesis
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . 63 B Hyperparameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75 LIST

  • Revenue-based spectrum management via Markov decision process

    Creator:
    Zhu, Pingan
    Abstract:
    We consider the problem of wireless spectrum management in cognitive wireless networks that maximizes the revenue for a spectrum operator. Specifically, we study the problem on how a wireless spectrum operator can optimally allocate its limited spectrum to various classes users/devices who pay differently for their spectrum per unit time....
    Resource Type:
    Masters Thesis
    Full Text:
    A Proof for Optimality of Backward Induction . . . . . . . . . . . . . . . . . . 39 B Proof for

  • Efficient Algorithms for Robust Spatiotemporal Data Analysis

    Creator:
    Moore, Travis W.
    Abstract:
    Many large-scale data analysis applications involve data that can vary over both time and space. Often the primary goal of analyzing spatiotemporal data is identifying trends, movements, and sudden changes with respect to time, location, or both. This can include a variety of applications in economics (housing prices, unemployment, job...
    Resource Type:
    Dissertation
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80 B PCCA Likelihood Gradient . . . . . . . . . . . . . . . . . . . . . . . . . . . 81 LIST OF

  • Protein secondary structure prediction using conditional random fields and profiles

    Creator:
    Shen, Rongkun
    Abstract:
    Protein secondary structure prediction plays a pivotal role in predicting protein folding in three-dimensions. Its task is to assign each residue one of the three secondary structure classes helix, strand, or random coil. This is an instance of the problem of sequential supervised learning in machine learning. This thesis describes...
    Resource Type:
    Masters Thesis
    Full Text:
    j i j i j j j i a a j i j b b j i j i j j j i a b J P Y X y X y y X Z X y X y y X Z X g y X f y