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 9 of 9 for “"Computer science Statistical methods"”.

  1. A Unique Method of Using Information Entropy to Evaluate the Reliability of Deep Neural Network Predictions on Intracranial Electroencephalogram

    … to a specific decision by DNN. One of the common methods of addressing this question involve generation of heatmaps. Another pertinent question is how effectively DNN has captured the entire information presented in the input, which can potentially be addressed with complexity measures of the …

    ucf Repository record for A Unique Method of Using Information Entropy to Evaluate the Reliability of Deep Neural Network Predictions on Intracranial Electroencephalogram (opens in a new tab)

  2. Classification of Ground-Truth Fire Debris Samples Using Neural Networks

    Fire debris samples are currently analyzed according to ASTM E1618-19, which is the "Standard Test Method for Ignitable Liquid Residues in Extracts from Fire Debris Samples by Gas Chromatography-Mass Spectrometry." This method requires that an analyst make a visual comparison to an appropriate …

    ucf Repository record for Classification of Ground-Truth Fire Debris Samples Using Neural Networks (opens in a new tab)

  3. Function Approximation Guarantees for a Shallow Neural Network Trained by Gradient Flow

    … functions, with better accuracy than classical methods. The bulk of approximation theory results though, are only concerned with the infimum error for all possible parameterizations of a given network size. Their proofs often rely on hand-crafted networks, where the weights and biases are …

    ucf Repository record for Function Approximation Guarantees for a Shallow Neural Network Trained by Gradient Flow (opens in a new tab)

  4. On Patching Learning Discrepancies in Neural Network Training

    Neural network's ability to model data patterns proved to be immensely useful in a plethora of practical applications. However, using the physical world's data can be problematic since it is often cluttered, crowded with scattered insignificant patterns, contain unusual compositions, and widely …

    ucf Repository record for On Patching Learning Discrepancies in Neural Network Training (opens in a new tab)

  5. Towards Robust Artificial Intelligence Systems

    … FGSM, PGD, DeepFool, CW, and adversarial patch methods. For a DNN trained on MNIST images, ABC metric is high for in-distribution MNIST input and low for out-of-distribution Fashion-MNIST and notMNIST input.

    ucf Repository record for Towards Robust Artificial Intelligence Systems (opens in a new tab)

  6. Methods For Defending Neural Networks Against Adversarial Attacks

    … frontier of the revolution within the field of computer vision. Since the advent of AlexNet in 2012, neural networks with CNN architectures have surpassed human-level capabilities for many cognitive tasks. As the neural networks are integrated in many safety critical applications such as …

    ucf Repository record for Methods For Defending Neural Networks Against Adversarial Attacks (opens in a new tab)

  7. A Topic Modeling approach for Code Clone Detection

    In this thesis work, the potential benefits of Latent Dirichlet Allocation (LDA) as a technique for code clone detection has been described. The objective is to propose a language-independent, effective, and scalable approach for identifying similar code fragments in relatively large software …

    unf Repository record for A Topic Modeling approach for Code Clone Detection (opens in a new tab) Download PDF for A Topic Modeling approach for Code Clone Detection (opens in a new tab)

  8. Semi-supervised learning in exemplar based neural networks

    A new and novel method for training exemplar based neural networks called Semisupervised learning is introduced. Semi-supervised learning (SSL) refers to the semisupervised manner according to which exemplars are formed during training to identify clusters. Instead of forcing a neural network to …

    ucf Repository record for Semi-supervised learning in exemplar based neural networks (opens in a new tab)