Search Constraints

Start Over
Filtering by: Creator Robinson, Max Edward Remove constraint Creator: Robinson, Max Edward Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad

Search Results

  • Learning and Improving Policies for Probabilistic Planning Problems

    Creator:
    Issakkimuthu, Murugeswari
    Abstract:
    In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
    Resource Type:
    Dissertation

  • Bayesian optimization with empirical constraints

    Creator:
    Azimi, Javad
    Abstract:
    Bayesian Optimization (BO) methods are often used to optimize an unknown function f(•) that is costly to evaluate. They typically work in an iterative manner. In each iteration, given a set of observation points, BO algorithms select k ≥ 1 points to be evaluated. The results of those points are...
    Resource Type:
    Dissertation
    Full Text:
    ) with the highest probability: x∗ = arg max x p(y(x) ≥ (1 + α)ymax), (2.3) where y is the output

  • Analytical Methods for Improving Causal Inference

    Creator:
    Sinha, Meghamala
    Abstract:
    Causal inference is an important analytical tool to bridge the gap between prediction and decision-making. However, learning a causal network solely from data is a challenging task. In this work, various techniques have been explored for a better and improved causal network learning from data. Firstly, the problem of learning...
    Resource Type:
    Dissertation

  • Leveraging Structures of the Data in Deep Learning

    Creator:
    Li, Xingyi
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    . . . . . . . . . . . . . . . . . . . 12 2.3.3 Accounting for Max-Pooling by Average Pooling . . . . . . . . . . 13 2.4 Problem Domains

  • Structured learning with latent variables : theory and algorithms

    Creator:
    Zhao, Kai
    Abstract:
    Most tasks in natural language processing (NLP) try to map structured input (e.g., sentence or word sequence) to some form of structured output (tag sequence, parse tree, semantic graph, translated/paraphrased/compressed sentence), a problem known as “structured prediction”. While various learning algorithms such as the perceptron, maximum entropy, and expectation-maximization have...
    Resource Type:
    Dissertation
    Full Text:
    SVM [54] and Max-Margin Markov Networks (M3N) [52]. Furthermore, neural network models also evolve to

  • Separabilities for a new class of gray codes

    Creator:
    Park, Jung Pil
    Resource Type:
    Capstone Project
    Full Text:
    Without loss of generality, assume i > j. Let Ii- j I max be the maximum distance between i and j

  • Learning with Partial Supervision for Clustering and Classification

    Creator:
    Pei, Yuanli
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    incorporated as max A fA + α 2M2 ∑ (i,j) ∑ (r,s) [ΩL(i, j)− ΩL(r, s)][ΩA(i, j)− ΩA(r, s)] (2.2) where M

  • Improving and Understanding Deep Models for Natural Language Comprehension

    Creator:
    Ghaeini, Reza
    Abstract:
    Natural Language Comprehension is a challenging domain of Natural Language Processing. To improve a model’s language comprehension/understanding, one approach would be to enrich the structure of the model to enhance its capability in learning the latent rules of the language. In this dissertation, we will first introduce several deep models...
    Resource Type:
    Dissertation
    Full Text:
    ReLU(x) = max(0, x) Figure 2.1: Three most commonly used non-linear activation functions in neural net

  • The density signature

    Creator:
    Migler-VonDollen, Theresa
    Abstract:
    In real networks, identifying dense regions is of great importance. For example, in a network that represents academic collaboration, authors within the densest component of the graph tend to be the most prolific. Dense subgraphs often identify communities in social networks. And dense subgraphs can be used to discover regulatory...
    Resource Type:
    Dissertation
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.2 A graph with a different min-max and min-lex orientations . . . . . . . . 11 2.3 The

  • Investigating Latent State and Uncertainty Representations in Reinforcement Learning

    Creator:
    Koul, Anurag
    Abstract:
    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...
    Resource Type:
    Dissertation