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 23 for “"Modular Neural Network"”.

  1. An ensemble and modular neural network approach to the diagnosis of acute appendicitis

    … with an accuracy rate between 75-80%. Artificial neural networks perform quite well with complex tasks such as pattern networks have been applied to many areas of the medical field for analysis of various diseases and conditions. Application of artificial neural networks to the diagnosis of acute …

    manitoba Repository record for An ensemble and modular neural network approach to the diagnosis of acute appendicitis (opens in a new tab)

  2. Application of neural networks to interpretation of well logs

    … and are not suitable for well-site applications. Neural networks provide a means for building fast and robust modeling and inversion algorithms that can be applied at well sites without calling for intensive computer resources. Several neural networks were applied and compared to interpret well …

    arizona-thes Repository record for Application of neural networks to interpretation of well logs (opens in a new tab)

  3. Computational meta-analysis of protein interaction data

    … and user interface components. Even though neural network has been proven a good approach in machine learning, it has not been popular in proteomic studies because of categorical data description and data size in those applications. In order to avoid these problems, this study adopts …

    wayne-thes Repository record for Computational meta-analysis of protein interaction data (opens in a new tab)

  4. Biologically Inspired Modular Neural Networks

    This dissertation explores the modular learning in artificial neural networks that mainly driven by the inspiration from the neurobiological basis of the human learning. The presented modularization approaches to the neural network design and learning are inspired by the engineering, complexity, …

    vt Repository record for Biologically Inspired Modular Neural Networks (opens in a new tab)

  5. A Study in Speaker Dependent Medium Vocabulary Word Recognition: Application to Human/Computer Interface

    … whenever the vocabulary is extended. A novel modular neural network architecture, called a Pyramidal Modular Neural Network (PMNN), is introduced for recursive speech identification. In addition, many other system algorithms/components, such as speech endpoint detection, automatic noise …

    vt Repository record for A Study in Speaker Dependent Medium Vocabulary Word Recognition: Application to Human/Computer Interface (opens in a new tab)

  6. Scene interpretation and object recognition for mobile robots equipped with cameras

    … image. The recognition step is built around a modular neural network (MNN) trained using backpropagation into which colour histograms and eigenimage projection coefficients are fed as main cues along with simple region information. The detection approach was found to be 45 times faster than an …

    chalmers Repository record for Scene interpretation and object recognition for mobile robots equipped with cameras (opens in a new tab)

  7. Utilizing symmetry in evolutionary design

    … an approach called ENSO is developed to evolve modular neural network controllers for simulated multilegged robots. Inspired by how symmetric organisms have evolved in nature, ENSO utilizes group theory to break symmetry systematically, constraining evolution to explore promising regions of the …

    texas Repository record for Utilizing symmetry in evolutionary design (opens in a new tab)

  8. Modelagem da vida em fadiga de compósitos poliméricos por redes neurais modulares: influência da inicialização de pesos e do tipo de algoritmo de treinamento

    … ratios. This work evaluates the application of a Modular Neural Network architecture for predicting the fatigue strength of glass fiber- and carbon fiber-reinforced laminates, investigating different training configurations, including the Backpropagation (BP) and Levenberg–Marquardt (LM) …

    brazil-ufrn Repository record for Modelagem da vida em fadiga de compósitos poliméricos por redes neurais modulares: influência da inicialização de pesos e do tipo de algoritmo de treinamento (opens in a new tab)

  9. Explaining time series data with interpretable modular neural networks

    … to meteorology and life sciences. Although deep neural networks (DNNs) have shown excellent predictive performance for time series, they have been criticised for being non-interpretable. Neural Additive Models, however, are known to be fully-interpretable by construction, but may achieve far …

    city-london Download PDF for Explaining time series data with interpretable modular neural networks (opens in a new tab)

  10. Transformer-Based lithuanian text stressing for speech synthesis /

    … synthesis. The proposed approach introduces a modular neural network that explicitly assigns stress marks prior to synthesis, aiming to improve stress realization in synthesized speech. Two core hypotheses were investigated: (1) that a neural network model can outperform prominent rule-based …

    vilnius Repository record for Transformer-Based lithuanian text stressing for speech synthesis / (opens in a new tab)

  11. Artificial Neural Networks and Map-Matching for GPS Navigation

    … the computed system location with a digital map network. Map Matched GPS (MMGPS) is a test-bed simulator for researching algorithms and techniques to reduce the error in position provided by a low cost stand-alone GPS receiver. In order to correctly map-match the GPS positions, a decision about …

    southwales Repository record for Artificial Neural Networks and Map-Matching for GPS Navigation (opens in a new tab) Download PDF for Artificial Neural Networks and Map-Matching for GPS Navigation (opens in a new tab)

  12. Pushing the frontier of quantum many-body simulation using classical computers

    … atom-based quantum processors. By designing a modular neural network architecture and training it on realistic error models, we achieve competitive decoding accuracy and efficiency. Our work highlights the potential of classical machine learning to enhance the performance of quantum error …

    cornell Repository record for Pushing the frontier of quantum many-body simulation using classical computers (opens in a new tab)

  13. A study of lower ionosphere and seismic interactions activity using a radiowave receiver network

    … Processing methods, including the application of neural networks, in the study of lower ionosphere, and the seismic interactions before, during and after an earthquake. An introduction and analysis of the building blocks of the interactions from a geophysical perspective, and the different …

    greece Repository record for A study of lower ionosphere and seismic interactions activity using a radiowave receiver network (opens in a new tab)

  14. The use of neural networks in the combining of time series forecasts with differential penalty costs

    … of this study is to examine the usefulness of neural networks in composite forecasting. Emphasis is placed on the effectiveness of two neural networks (i.e., a backpropagation neural network and a modular neural network) relative to three traditional composite models (i.e., a simple average, a …

    vt Repository record for The use of neural networks in the combining of time series forecasts with differential penalty costs (opens in a new tab)

  15. Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults

    … fault. The AI techniques include artificial neural networks (ANN, or briefly neural networks - NN), expert systems, fuzzy systems and multivariate regression. The fault diagnosis is based on dissolved gas-in-oil analysis (DGA). A literature review showed that the conventional fault diagnosis …

    vt Repository record for Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults (opens in a new tab)

  16. Neural network interpretation of electromagnetic ellipticity data in a frequency range from 1 kHz to 32 MHz

    … and visualization scheme and software, using neural networks for the detection and localization of buried waste, and the boundaries of waste sites, has been developed. The capabilities and limitations of the high-frequency (1 kHz to 1 MHz and 31 kHz to 32 MHz) electromagnetic ellipticity …

    arizona-thes Repository record for Neural network interpretation of electromagnetic ellipticity data in a frequency range from 1 kHz to 32 MHz (opens in a new tab)

  17. Fault analysis on power systems using wavelet transformed transients and artificial intelligence

    … for fault analysis on typical distribution ring network. Using a hybrid of expert systems [ES] and small modular neural networks, called target neural networks trained to identify one specific condition each time, the concept is to reduce the scale of the problem systematically by using many …

    nus Repository record for Fault analysis on power systems using wavelet transformed transients and artificial intelligence (opens in a new tab) Download file for Fault analysis on power systems using wavelet transformed transients and artificial intelligence (opens in a new tab)

  18. INTEGRATED NEURAL NETWORK MODELLING OF CONSTRUCTION DEMAND IN SINGAPORE

    … a suitable construction demand model using neural networks that would help to overcome the problems associated with the traditional econometric models using conventional algorithms. The first stage of the III study involved a review of works on econometric models and identification of the …

    nus Repository record for INTEGRATED NEURAL NETWORK MODELLING OF CONSTRUCTION DEMAND IN SINGAPORE (opens in a new tab) Download file for INTEGRATED NEURAL NETWORK MODELLING OF CONSTRUCTION DEMAND IN SINGAPORE (opens in a new tab)

  19. DSP IMPLEMENTATION OF NEURAL NETWORK BASED ATM ABR TRAFFIC MANAGEMENT

    Congestion control in ATM networks has become a high priority in network design and research clue to a large increase in the number of bandwidth-intensive network applications. Recently, considerable efforts have been centered on traffic management of the available bit rate (ABR) service. Among the …

    nus Repository record for DSP IMPLEMENTATION OF NEURAL NETWORK BASED ATM ABR TRAFFIC MANAGEMENT (opens in a new tab) Download file for DSP IMPLEMENTATION OF NEURAL NETWORK BASED ATM ABR TRAFFIC MANAGEMENT (opens in a new tab)

  20. Applications of artificial neural networks in financial market forecasting

    This thesis evaluates the utility of Artificial Neural Networks (ANNs) applied to financial market and macroeconomic forecasting. In application, ANNs are evaluated in comparison to traditional forecasting models to evaluate if their nonlinear and adaptive properties yield superior forecasting …

    glasgow Repository record for Applications of artificial neural networks in financial market forecasting (opens in a new tab) Download PDF for Applications of artificial neural networks in financial market forecasting (opens in a new tab)

Page 1 of 2