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 7 of 7 for “"activation layer"”.

  1. On-Loom Fabric Defect Inspection Using Contact Image Sensors and Activation Layer Embedded Convolutional Neural Network

    … (4) introducing the novel pairwise-potential activation layer to a convolutional neural network that leads to high accuracies of defect segmentation on fabrics with fine and imbalanced structures, (5) achieving a real-time defect detection that allows a possible defect to be examined multiple …

    unt Repository record for On-Loom Fabric Defect Inspection Using Contact Image Sensors and Activation Layer Embedded Convolutional Neural Network (opens in a new tab)

  2. Effective Activation Functions for Homomorphic Evaluation of Deep Neural Networks

    … which can be homomorphically evaluated, layers such as the activation layer are non-linear and cannot be homomorphically evaluated. One of the most commonly used alternatives is approximating these non-linear functions using low-degree polynomials. However, it is difficult to generate …

    rit Repository record for Effective Activation Functions for Homomorphic Evaluation of Deep Neural Networks (opens in a new tab)

  3. The Effect Of Hyperparameters In The Activation Layers Of Deep Neural Networks

    … trainable hyperparameters into transformation layers (GRU [7], LSTM [13], etc), the introduction of hyperparameters into the activation layers have been largely ignored. This paper serves several purposes: to (1) equip the reader with the background knowledge, including theory and best …

    mississippi Repository record for The Effect Of Hyperparameters In The Activation Layers Of Deep Neural Networks (opens in a new tab)

  4. Exploring the Effectiveness of Privacy Preserving Classification in Convolutional Neural Networks

    … CNN with the creation of privacy-preserving CNN layers that have the ability to operate on encrypted images. This was accomplished through (1) researching the underlying structure of preexisting privacy-preserving CNN classifiers, (2) creating privacy-preserving convolution, pooling, and …

    rit Repository record for Exploring the Effectiveness of Privacy Preserving Classification in Convolutional Neural Networks (opens in a new tab)

  5. CHEMICAL CONTROL OF SEMICONDUCTOR SURFACE: XPS AND STM

    … removal of the TiO2 surface carboxylate layer. Furthermore, the development of a method to protect photocathodes with atomically thin coatings, such as single-layer graphene and hexagonal boron nitride, was discussed. The feasibility of this method was proved by fabricating protected Mg …

    cornell Repository record for CHEMICAL CONTROL OF SEMICONDUCTOR SURFACE: XPS AND STM (opens in a new tab)

  6. A Transfer Learning Approach to Object Detection Acceleration for Embedded Applications

    … a starting point then fine-tunes only the output layers for detection on more specific objects of five classes. The model architecture was then modified slightly for compatibility with the FPGA hardware using techniques such as weight quantization and replacing unsupported activation layer types. …

    iupui Repository record for A Transfer Learning Approach to Object Detection Acceleration for Embedded Applications (opens in a new tab)