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 63 for “"sigmoid"”.

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

    <p>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)

  2. Time Aware Sigmoid Optimization : a new learning rate scheduling method

    … training rate decay method called Training Aware Sigmoid Optimization (TASO), which proposes a dual-phase during training. The proposed method aims to improve training, achieving a better inference performance in a reduced amount of time. A series of tests were done to evaluate this hypothesis, …

    brazil-ufpe Repository record for Time Aware Sigmoid Optimization : a new learning rate scheduling method (opens in a new tab)

  3. DESIGNS FOR TESTING LACK OF FIT FOR A CLASS OF SIGMOID CURVE MODELS

    Sigmoid curves have found broad applicability in biological sciences and biopharmaceutical research during the last decades. A well planned experiment design is essential to accurately estimate the parameters of the model. In contrast to a large literature and extensive results on optimal designs …

    temple Repository record for DESIGNS FOR TESTING LACK OF FIT FOR A CLASS OF SIGMOID CURVE MODELS (opens in a new tab)

  4. Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function

    … ANN contributes to slow convergence caused by sigmoid function. Thus, this research proposes Hyperbolic Tangent activation function (Tanh) to be used in the hidden layer of the ANN architecture to produce faster convergence. Back-propagation learning algorithm is applied to the multilayer …

    uthm Repository record for Improving modified cocomo ii artificial neural network using hyperbolic tangent activation function (opens in a new tab)

  5. Abnormal cell patterning at the cortical gray-white matter boundary in autism spectrum disorders

    … and dorsal parietal lobe (BA 7) of each case. A sigmoid curve was fitted to the transition zone between layer VI and underlying white matter (subplate), and the slope of the resulting curve was used as a measure of the spatial extent of the transition zone. For all three cortical regions …

    unr Repository record for Abnormal cell patterning at the cortical gray-white matter boundary in autism spectrum disorders (opens in a new tab)

  6. Hydraulic properties of asphalt concrete

    … that asphalt concrete may require bi-modal sigmoid curves to represent drying. It is also proposed that asphalt concrete is a hydrophobic material during wetting and a hydrophilic material during drying. The wetting curves developed for the asphalt concrete were fit with power functions, …

    unm Repository record for Hydraulic properties of asphalt concrete (opens in a new tab)

  7. Sigmond Colon Volvulus Management: An analysis of factors contributing to morbididty amd mortality in single and double stage operations

    … to morbidity and mortality in the treatment of sigmoid colon volvulus and also compare the outcome of single stage versus double stage operations. Fifty four consecutive patients presenting to the UTH with sigmoid volvulus were entered into the study. Fifty two were treated as emergency cases …

    zambia Repository record for Sigmond Colon Volvulus Management: An analysis of factors contributing to morbididty amd mortality in single and double stage operations (opens in a new tab)

  8. Automated Treatment Planning in High Dose-Rate Brachytherapy for Cervical Cancer

    … models to segment the bladder, rectum, and sigmoid colon automatically, organs of particular importance for cervical cancer HDRBT. In Chapter 4, I present integration of the organ segmentation modules and other modules into the AutoBrachy system for clinical use to automate the planning …

    utswmed Repository record for Automated Treatment Planning in High Dose-Rate Brachytherapy for Cervical Cancer (opens in a new tab)

  9. An Ordinary Differential Equation Based Model For Clustering And Vector Quantization

    … system is also introduced. This system utilizes sigmoid and competitive functions. Although the results of this system are encouraging, the use of sigmoid function makes analyze and study stability of the system extremely difficult.

    siu-theses Repository record for An Ordinary Differential Equation Based Model For Clustering And Vector Quantization (opens in a new tab)

  10. Laparoscopy and loop colostomy : a new approach to extra-peritoneal rectal injuries

    … of laparoscopy and the formation of a diverting sigmoid loop colostomy through an abdominal wall trephine, in a limited number of carefully selected patients with isolated extra-peritoneal rectal injuries. The patient is thus spared a major laparotomy wound. The value of distal rectal washout and …

    cape-town Repository record for Laparoscopy and loop colostomy : a new approach to extra-peritoneal rectal injuries (opens in a new tab)

  11. Wrist Motion Simulation With a Rigid Body Spring Model Comparing Different Elements Modeling Approaches

    … computed using either exponential function or sigmoid function in two different models. Each of these force functions were proportional to the distance between the simulation capitate and the capitate in the desired position. Capitate was chosen as tracking marker because the common center of …

    queens Repository record for Wrist Motion Simulation With a Rigid Body Spring Model Comparing Different Elements Modeling Approaches (opens in a new tab)

  12. Design and Development of a Minimally Invasive Endoscope: Highly Flexible Stem with Large Deflection and Stiffenable Exoskeleton Structure

    … structure and simulated its behavior in a sigmoid colon model. To predict just how pointed an endoscope can be without damaging tissue under a given force, we extrapolated a strength model of the descending colon from published stress-strain curves of human colon tissue. Next we analyzed …

    vt Repository record for Design and Development of a Minimally Invasive Endoscope: Highly Flexible Stem with Large Deflection and Stiffenable Exoskeleton Structure (opens in a new tab)

  13. The thermal decomposition of unirradiated and irradiated lithium azide

    … decay period reaction rater The p/t plots were sigmoid, as found for the unirradiated azide. Applicability of the Avrami-Enofeyev equation in the analysis of the acceleratory period for the irradiated azide indicated that two-dimensional nuclei formed and grew on the surfaces of the particles, …

    cape-town Repository record for The thermal decomposition of unirradiated and irradiated lithium azide (opens in a new tab)

  14. Intrinsic Neural Control of Propulsion, Storage and Slow Transit in the Large Intestine.

    … (CM) of both the guinea pig distal and primate sigmoid colons. This activity has been referred to as ongoing peristaltic reflex activity. The sensory elements underlying the repetitive firing of ascending excitatory and descending inhibitory neuronal pathways lie in the CM, in close opposition …

    unr Repository record for Intrinsic Neural Control of Propulsion, Storage and Slow Transit in the Large Intestine. (opens in a new tab)

  15. Joint Training Methods for Tandem and Hybrid Speech Recognition Systems using Deep Neural Networks

    … the most common hidden activation functions, the sigmoid and rectified linear unit (ReLU), are parameterised to enable automatic learning of function forms. Experiments using conversational telephone speech (CTS) Mandarin data result in an average of 3.4% and 2.2% relative character error rate …

    cambridge Repository record for Joint Training Methods for Tandem and Hybrid Speech Recognition Systems using Deep Neural Networks (opens in a new tab)

  16. Η ΠΑΝΣΙΓΜΟΕΙΔΟΣΚΟΠΗΣΙΣ ΕΙΣ ΤΗΝ ΑΝΙΧΝΕΥΣΙΝ ΤΩΝ ΟΡΘΟΚΟΛΙΚΩΝ ΟΓΚΩΝ ΚΑΙ Η ΣΗΜΑΣΙΑ ΑΥΤΗΣ ΕΙΣ ΤΗΝ ΠΡΟΛΗΨΙΝ ΤΟΥ ΚΑΡΚΙΝΟΥ ΤΟΥ ΠΑΧΕΟΣ ΕΝΤΕΡΟΥ

    … SYMPTOMS HAVE BEEN EVALUATED WITH THE TCF-1S PANSIGMOIDOSCOPE FROM JANUARY 1979 TO DECEMBER 1980. THE FOLLOWING TECHNICAL PERFORMANCE HAVE ANALYSED: ADEQUATE PREPARATION IN 80% OF CARE, GOOD ACCEPTANCE IN84%, AVERAGE DISTANCE REACHED 51 CM, THE TIME REQUIRED FOR THE EXAM WAS LIMITED TO 10 MIN. …

    greece Repository record for Η ΠΑΝΣΙΓΜΟΕΙΔΟΣΚΟΠΗΣΙΣ ΕΙΣ ΤΗΝ ΑΝΙΧΝΕΥΣΙΝ ΤΩΝ ΟΡΘΟΚΟΛΙΚΩΝ ΟΓΚΩΝ ΚΑΙ Η ΣΗΜΑΣΙΑ ΑΥΤΗΣ ΕΙΣ ΤΗΝ ΠΡΟΛΗΨΙΝ ΤΟΥ ΚΑΡΚΙΝΟΥ ΤΟΥ ΠΑΧΕΟΣ ΕΝΤΕΡΟΥ (opens in a new tab)

  17. A Game-theoretic Analysis of Link Adaptation in Cellular Radio Networks

    … function selection, which uses the accurate sigmoid model for approximating throughput. The discrete action space makes it difficult to verify the existence of a Nash Equilibrium (NE) in this game using standard techniques. To circumvent this limitation, a heuristic algorithm is proposed. …

    vt Repository record for A Game-theoretic Analysis of Link Adaptation in Cellular Radio Networks (opens in a new tab)

  18. Using Lipid Bilayers in an Artificial Axon System

    … channels in a real axon in that they follow a sigmoid activation curve in response to a step potential change.

    vt Repository record for Using Lipid Bilayers in an Artificial Axon System (opens in a new tab)

  19. Investigation of slow oscillations in blood pressure

    … function representation of the nonlinear sigmoid characteristic inherent to the baroreflex, led to the investigation of a range of describing function approximation methods for the sigmoid nonlinearity, which permeates the cardiovascular literature. A nonlinear model of the complete …

    maynooth Repository record for Investigation of slow oscillations in blood pressure (opens in a new tab)

  20. Optimization of coded signals based on wavelet neural network

    … a new class of network that combines the classic sigmoid neural network and wavelet analysis. We performed a simulation to evaluate the effectiveness of the proposed method. The simulation results demonstrated great approximation ability of WNN and its ability in prediction and system modeling. We …

    uthm Repository record for Optimization of coded signals based on wavelet neural network (opens in a new tab)

Page 1 of 4