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 228 for “"activation function"”.

  1. TeLU Activation Function for Fast and Stable Deep Learning

    … Linear Unit (TeLU), a neural network hidden activation function defined as $TeLU(x)=x \cdot tanh(e^x)$. TeLU’s design is grounded in the core principles of key activation functions, achieving strong convergence by closely approximating the identity function in its active region while …

    usf Repository record for TeLU Activation Function for Fast and Stable Deep Learning (opens in a new tab)

  2. INITIALIZATION STRATEGY AND ACTIVATION FUNCTION SELECTION FOR NEURAL NETWORKS BASED ON GAUSSIAN PROCESS OPTIMIZATION

    … choosing appropriate initialization schemes and activation functions remains an important research topic within the deep learning and machine learning communities. My dissertation studies the connection between Gaussian processes and neural networks. It seeks to leverage their synergies to …

    iu Repository record for INITIALIZATION STRATEGY AND ACTIVATION FUNCTION SELECTION FOR NEURAL NETWORKS BASED ON GAUSSIAN PROCESS OPTIMIZATION (opens in a new tab)

  3. Hopf bifurcation as an activation function for complex recurrent neural networks: A feasibility study

    … relies on the selection of an appropriate activation function. Some established activation functions, known to enhance complex-valued recurrent networks, are chosen based on specific network properties. Exploring alternative approaches to complex activation holds promise for improving the …

    iastate Repository record for Hopf bifurcation as an activation function for complex recurrent neural networks: A feasibility study (opens in a new tab)

  4. Autophagy: activation, function and regulation by a protein restricted diet during pregnancy and lactation

    … the role that HDAC3 may play in the activation of LC3B and lipid accumulation will bring valuable insight into the epigenetic control of hepatic lipid accumulation by a LP diet during pregnancy and lactation in rat dams. In summary, our results demonstrate that protein restriction …

    uiuc Repository record for Autophagy: activation, function and regulation by a protein restricted diet during pregnancy and lactation (opens in a new tab)

  5. The Effect of a Missing at Random Missing Data Mechanism on a Single Layer Artificial Neural Network with a Sigmoidal Activation Function and the Use of Multiple Imputation as a Correction

    … layer artificial neural network with a sigmoidal activation function, equivalent to a binary logistic regression. Binary logistic regression is frequently used in health research and so it is a logical starting point to understand the effects of missing data on statistical learning models that …

    wvu Repository record for The Effect of a Missing at Random Missing Data Mechanism on a Single Layer Artificial Neural Network with a Sigmoidal Activation Function and the Use of Multiple Imputation as a Correction (opens in a new tab)

  6. Implementation of a New Sigmoid Function in Backpropagation Neural Networks.

    This thesis presents the use of a new sigmoid activation function in backpropagation artificial neural networks (ANNs). ANNs using conventional activation functions may generalize poorly when trained on a set which includes quirky, mislabeled, unbalanced, or otherwise complicated data. This new …

    etsu Repository record for Implementation of a New Sigmoid Function in Backpropagation Neural Networks. (opens in a new tab) Download PDF for Implementation of a New Sigmoid Function in Backpropagation Neural Networks. (opens in a new tab)

  7. The application of FEM technique to electromagnetic models for magnetic neural stimulation

    … along the nerve fiber path 82V/82 called the "activation function". If two magnetic coils have the same outer diameter than the one with the larger inner diameter will induce the largest electric field and activation function. This result has direct clinical implications for modern commercial …

    ubc Repository record for The application of FEM technique to electromagnetic models for magnetic neural stimulation (opens in a new tab) Download PDF for The application of FEM technique to electromagnetic models for magnetic neural stimulation (opens in a new tab)

  8. Bifurcation Portrait of a Hybrid Spiking Neuron Model

    … on a previous hybrid model with a convex spike-activation function f(x), but modified with a conductance reversal potential term. We analyze the model proposed by Izhikevich and obtain a bifurcation portrait for the continuous dynamics for an arbitrary convex spike activation function f(x). Both …

    ndsu Repository record for Bifurcation Portrait of a Hybrid Spiking Neuron Model (opens in a new tab)

  9. Physics Informed Neural Network for Solute Transport Phenomena in Heterogeneous Media

    … Neural Networks (PiNN) with a periodic activation function to solve solute transport problems in both homogeneous and heterogeneous porous media governed by the advection-dispersion equation. Unlike traditional neural networks that rely on large training datasets, PiNNs use strong-form …

    texas-state Repository record for Physics Informed Neural Network for Solute Transport Phenomena in Heterogeneous Media (opens in a new tab)

  10. A Comparison of Image Classification with Different Activation Functions in Balanced and Unbalanced Datasets

    … on the network structure design but also on the activation function performance. To identify an optimal activation function, this study investigates the correlation between the activation function selection and image classification performance in balanced or imbalanced datasets. Our analysis …

    vt Repository record for A Comparison of Image Classification with Different Activation Functions in Balanced and Unbalanced Datasets (opens in a new tab)

  11. Late residual neural networks: an approach to combat the dead ReLU problem

    The rectified linear unit (ReLU) activation function has been a staple tool in deep learning to increase the performance of deep neural network architectures. However, the ReLU activation function has trade-offs with its performance, specifically the dead ReLU problem caused by vanishing gradients. …

    colostate Repository record for Late residual neural networks: an approach to combat the dead ReLU problem (opens in a new tab)

  12. A 3D ray traced biological neural network learning model and applications

    … for contact tracing, is selecting the optimal activation function because there are many activation functions in the literature. A universal activation function (UAF) is proposed in the dissertation to solve the optimal activation function problem by evolving the UAF to a suitable activation …

    uvic Repository record for A 3D ray traced biological neural network learning model and applications (opens in a new tab)

  13. REGULARIZATION ON MACHINE LEARNING

    … regularization method called Drop-Activation. At the training phase, we drop nonlinear activation functions randomly and set them to be identity functions. At the testing phase, a deterministic network with a new activation function is used and the new activation function is …

    nus Repository record for REGULARIZATION ON MACHINE LEARNING (opens in a new tab) Download file for REGULARIZATION ON MACHINE LEARNING (opens in a new tab)

  14. Finite Element Model of an Active Material to Study Myocardial Contraction Pattern

    … passive by assigning a zero coefficient for the activation function. With proper selection of suitable material properties and activation function, their effect on left ventricular deformation pattern can be demonstrated. In this analysis, typical 'Normal', ' Tschemic' and 'Aneurysmal' …

    marquette Repository record for Finite Element Model of an Active Material to Study Myocardial Contraction Pattern (opens in a new tab)

  15. Implementation Costs of Spiking versus Rate-Based ANNs

    … multiplications, evaluation of a transcendental activation function, and transfer of its output to a large number of other neurons. These restrictions become more expensive when internal values are represented with increasingly higher data precision. A spiking neural network eliminates the …

    south-carolina Repository record for Implementation Costs of Spiking versus Rate-Based ANNs (opens in a new tab)

  16. Explore and Design Novel Structures for More Efficient and Better Deep Convolutional Neural Networks

    … perspective is to design a more powerful activation function, we design a unique Look-up Table Unit activation function that learns the shape of the activation function from the data and provides sufficient non-linearity to the network to learn more complex feature representations. We also …

    ucf Repository record for Explore and Design Novel Structures for More Efficient and Better Deep Convolutional Neural Networks (opens in a new tab)

  17. Neural Network in Hardware

    … (MNIST) database. A novel hardwarefriendly activation function called the dynamic ReLU (D-ReLU) function is proposed. This activation function can decrease chip area and power of neural networks when compared to traditional activation functions at no cost to prediction accuracy. The …

    unlv Repository record for Neural Network in Hardware (opens in a new tab) Download PDF for Neural Network in Hardware (opens in a new tab)

  18. Human Estrogen Receptor(alpha) Activity on Estrogen Responsive, Integrated Chloramphenicol Acetyltransferase (Cat) Reporter Constructs in Chinese Hamster Ovary (Cho) Cells

    … containing only AF1 elicited a dose dependent activation of the 2ERETKCAT promoter. This represents the first report of activation of an integrated reporter gene by this activation function.

    uiuc Repository record for Human Estrogen Receptor(alpha) Activity on Estrogen Responsive, Integrated Chloramphenicol Acetyltransferase (Cat) Reporter Constructs in Chinese Hamster Ovary (Cho) Cells (opens in a new tab)

  19. Training and performance improvement techniques for artificial neural networks

    … handled, based on evaluation of a probabilistic function that attempts to identify a portion of the unknown data that are most probably classified correctly and those that need to be reclassified from the beginning. The correctly identified data can be used during a second training process in …

    greece Repository record for Training and performance improvement techniques for artificial neural networks (opens in a new tab)

  20. Models for calculating confidence intervals for neural networks

    … hidden layer had a logistic or binary sigmoidal activation function and the output layer had a linear activation function. These techniques were tested on various data sets with and without additional noise. Out of eight cases studied, non-linear regression and bootstrapping each had the four …

    wvu Repository record for Models for calculating confidence intervals for neural networks (opens in a new tab)

Page 1 of 12