Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 46 for “"Pruning Algorithm"”.

  1. An adaptive pruning algorithm for DNN compression

    … and mobile platforms. Techniques such as pruning, quantization and binarization have been developed to reduce network parameter size. Pruning is the one of well-studied methods to solve network over-parameterization and reduce computational complexity. A typical pruning process includes …

    uiuc Repository record for An adaptive pruning algorithm for DNN compression (opens in a new tab)

  2. A pruning algorithm for one player games with hidden information

    … three contributions to the development of search algorithms for one-player games with hidden information. The first contribution is the description and analysis of a new pruning technique, called information set pruning, that is specific to hidden information games. Second, the One-Player Pruning …

    ut-knoxville Repository record for A pruning algorithm for one player games with hidden information (opens in a new tab)

  3. Resource-constraint And Scalable Data Distribution Management For High Level Architecture

    In this dissertation, we present an efficient algorithm, called P-Pruning algorithm, for data distribution management problem in High Level Architecture. High Level Architecture (HLA) presents a framework for modeling and simulation within the Department of Defense (DoD) and forms the basis of IEEE …

    ucf Repository record for Resource-constraint And Scalable Data Distribution Management For High Level Architecture (opens in a new tab)

  4. Solving the maximum clique problems on a class of network graphs, with applications to social networks

    … problem on undirected graphs and develop two algorithms to solve it: a pruning algorithm and an enumeration algorithm. The pruning algorithm successively improves an upper bound on the clique number of a graph, and the enumeration algorithm successively finds larger and larger cliques in the …

    nps Repository record for Solving the maximum clique problems on a class of network graphs, with applications to social networks (opens in a new tab)

  5. An Analysis Of Misclassification Rates For Decision Trees

    … on k-norm estimation suggests an efficient pruning algorithm that has a clear theoretical interpretation, is easily implemented, and does not require a validation set. Our experiments show that our proposed pruning algorithm produces accurate trees quickly that compares very favorably with …

    ucf Repository record for An Analysis Of Misclassification Rates For Decision Trees (opens in a new tab)

  6. Accelerating lattice scoring of automatic speech recognition through acoustic pre-pruning on GPU

    This thesis introduces an acoustic pre-pruning algorithm that speeds up lattice scoring for GMM based ASR systems, and a constrained agglomerative clustering algorithm that makes it possible to maintain the advantage of the new algorithm in a GPU implementation. The implementation undergoes 2% to …

    uiuc Repository record for Accelerating lattice scoring of automatic speech recognition through acoustic pre-pruning on GPU (opens in a new tab)

  7. Data Mining in Tree-Based Models and Large-Scale Contingency Tables

    … and data mining. We propose a novel tree-pruning algorithm called frontier-based tree-pruning algorithm (FBP). The new method has an order of computational complexity comparable to cost-complexity pruning (CCP). Regarding tree pruning, it provides a full spectrum of information. Numerical …

    gatech Repository record for Data Mining in Tree-Based Models and Large-Scale Contingency Tables (opens in a new tab)

  8. Zonotope matching and approximation for neural networks

    … equality must hold. In addition, we provide an algorithm and framework for approximating arbitrary polytopes by zonotopes using techniques from subgradient descent. Finally, we combine these two results to provide a novel neural network pruning algorithm based on the geometry of zonotope …

    texas Repository record for Zonotope matching and approximation for neural networks (opens in a new tab)

  9. Board game ai development using alpha-beta pruning /

    … for a board game "Gipf" using alpha-beta pruning algorithm. This algorithm is precomputing game strategies for every possible step prior to next turn. The board game itself is an abstract type, thus do not have any random or luck based events and relies on player strategies. The game was …

    vilnius Repository record for Board game ai development using alpha-beta pruning / (opens in a new tab)

  10. Neural Network Pruning for ECG Arrhythmia Classification

    … made in effectively reducing these overheads by pruning and compressing large CNNs with only a slight decline in model accuracy. In this study, two pruning methods are implemented and compared on the CIFAR-10 database and an ECG arrhythmia classification task. Each pruning method employs a …

    calpoly Repository record for Neural Network Pruning for ECG Arrhythmia Classification (opens in a new tab)

  11. Correlation-based Analytics in Big Data

    … proven Theories and Lemmas, we develop a pruning algorithm to solve problems with a wide range of products. We use Dunnhumby dataset to illustrate effectiveness and efficiency of our algorithm. In this study, we illustrate the significance of items correlation and price-sensitivity in …

    utk-theses Repository record for Correlation-based Analytics in Big Data (opens in a new tab)

  12. Neural Networks in the Analysis of Water-Soluble Sulfonylurea Herbicides Using an LC/MS

    In this research, a hidden node pruning algorithm was developed for an artificial neural network (ANN) that automatically determined a more efficient size of the hidden layer, caused the ANN to resize itself, and then continued to train using a standard back-propagation algorithm. The hidden-node …

    vcu Repository record for Neural Networks in the Analysis of Water-Soluble Sulfonylurea Herbicides Using an LC/MS (opens in a new tab)

  13. TOWARD A RUNTIME PROGRAMMABLE SPIKING NEURAL NETWORK HARDWARE ACCELERATOR WITH ON-CHIP LEARNING

    … (SNNs), energy-efficient machine learning algorithms inspired by the activities of the biological brain. Due to their event-driven nature, SNNs are expected to consume less energy than Artificial Neural Networks (ANNs). However, implementing complex SNNs that achieve satisfactory accuracy …

    nus Repository record for TOWARD A RUNTIME PROGRAMMABLE SPIKING NEURAL NETWORK HARDWARE ACCELERATOR WITH ON-CHIP LEARNING (opens in a new tab) Download file for TOWARD A RUNTIME PROGRAMMABLE SPIKING NEURAL NETWORK HARDWARE ACCELERATOR WITH ON-CHIP LEARNING (opens in a new tab)

  14. Exploring redundancy in neural networks: pruning by genetic algorithm & filter energy

    … redundancy can be reduced. I contribute a weight pruning genetic algorithm, an energy-based filter pruning algorithm, and provide insights on model compression and structure. Evolved weight pruning of MNIST trained multilayer perceptrons and convolutional networks showed that in some cases 72.4% …

    manitoba Repository record for Exploring redundancy in neural networks: pruning by genetic algorithm & filter energy (opens in a new tab)

  15. Statistical Recursive Estimation Algorithms for Speaker Adaption

    … development of statistical recursive estimation algorithms for speaker adaptation. In this thesis, a unified framework for recursive maximum likelihood estimation and recursive Bayesian learning is first developed and applied to direct hidden Markov model parameter estimation. Then an online …

    uiuc Repository record for Statistical Recursive Estimation Algorithms for Speaker Adaption (opens in a new tab)

  16. An Exploration into the Effectiveness of Prefetching on Program Performance with the Help of an Autotuning Model

    … of a collection of programs and how learning algorithms can be used to predict the optimal hardware prefetching algorithms to obtain improved performance. Modern processors are equipped with several hardware prefetchers, each of which implements a different prefetching algorithm. My goal was …

    texas-state Repository record for An Exploration into the Effectiveness of Prefetching on Program Performance with the Help of an Autotuning Model (opens in a new tab)

  17. Sparse deep neural networks for modeling physical and biological systems

    … namely network motif theory. Neural network pruning is used to find a sparse computational model for controlling a biological motor task. Using a sequential, magnitude-based pruning algorithm, as many as 93\% of network parameters can be removed from a DNN without compromising performance. …

    washington Repository record for Sparse deep neural networks for modeling physical and biological systems (opens in a new tab)

  18. Learning from ambiguous examples for object detection and image categorization

    … are two-fold. Firstly, we propose a data pruning algorithm for identifying and removing mislabeled and hard-to-learn examples from the training set. Secondly, we proposed an effective feature selection method for selecting informative features from the training set. In the second half of …

    unsw Repository record for Learning from ambiguous examples for object detection and image categorization (opens in a new tab)

  19. Trustworthy AI in the Modern Era: Theories and Applications

    … into theoretical foundations and practical algorithms. Particularly, I focus on four interconnected critical components of modern AI: model security, fairness, explainability, and data privacy. For model security, I aim to ensure that the model integrity and behavior are not compromised …

    umn Repository record for Trustworthy AI in the Modern Era: Theories and Applications (opens in a new tab)

  20. Efficiency Advances in Moment Tensor Potentials for Machine-Learning Atomistic Modelling

    … contribution proposes a novel post-training pruning algorithm that is both data-driven and cost-aware, optimizing the MTP’s algorithmic structure and achieving up to sevenfold speedups. Collectively, these contributions establish a more efficient and scalable MTP framework, expanding the …

    queens Repository record for Efficiency Advances in Moment Tensor Potentials for Machine-Learning Atomistic Modelling (opens in a new tab)

Page 1 of 3