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 49 for “"neural net"”.

  1. Development and VLSI implementation of a new neural net generation method

    … begins with a short introduction to current neural network practices and pitfalls including an in depth discussion of the meaning behind the equations. Specifically, a description of the underlying processes involved is given which likens training to the biological process of cell …

    vt Repository record for Development and VLSI implementation of a new neural net generation method (opens in a new tab)

  2. Control and Convolutional Neural Net Based Pose Estimation for On-Orbit Assembly

    … feasibility. TESSERAE, or Tessellated Electromagnetic Space Structures for Exploration of Reconfigurable Adaptive Environments, a project out of the MIT Media Lab Space Exploration Initiative, is a multi-year research effort to develop a set of self-assembling, decentralized tiles that use …

    mit Repository record for Control and Convolutional Neural Net Based Pose Estimation for On-Orbit Assembly (opens in a new tab)

  3. Convolutional Neural Net Models and Image Processing Methods for Predicting Surgical Site Infection

    … image of a wound and then apply a convolutional neural network (CNN) model to identify features of infection. For this thesis, I have explored both RGB images captured using a mobile phone camera and also thermal images captured using an external thermal camera module. The data for this work was …

    mit Repository record for Convolutional Neural Net Models and Image Processing Methods for Predicting Surgical Site Infection (opens in a new tab)

  4. Single-Phase, Single-Switch, Sensorless Switched Reluctance Motor Drive Utilizing a Minimal Artificial Neural Net

    Artificial Neural Networks (ANNs) have proved to be useful in approximating non- linear systems in many applications including motion control. ANNs advocated in switched reluctance motor (SRM) control typically have a large number of neurons and several layers which impedes their real time …

    vt Repository record for Single-Phase, Single-Switch, Sensorless Switched Reluctance Motor Drive Utilizing a Minimal Artificial Neural Net (opens in a new tab)

  5. Fourier and Laplace Transform Methods for Linear Spatial-Temporal Neural Net Modelling, Applied to the Cerebellum

    Made available in DSpace on 2014-12-14T05:40:41Z (GMT). No. of bitstreams: 1 7606940.pdf: 2472491 bytes, checksum: cf07bc705beffcd135fe2359a49e275b (MD5) Previous issue date: 1975

    uiuc Repository record for Fourier and Laplace Transform Methods for Linear Spatial-Temporal Neural Net Modelling, Applied to the Cerebellum (opens in a new tab)

  6. A study of using backpropagation and a new neural net algorithm for edge detecting in binary images

    … research is to explore the possibility of using neural computing algorithms for edge detection in binary images. This paper presents the following : 1. the experimental results of using the basic backpropagation algorithm for edge detecting in binary images. 2. the development of a new neural

    eastern-wash Repository record for A study of using backpropagation and a new neural net algorithm for edge detecting in binary images (opens in a new tab)

  7. Developing neural network applications using LabVIEW

    Artificial Neural Networks (ANN) have gained tremendous popularity over the last few decades. They are considered as substitutes for classical techniques which have been followed for many years. Many neural network architectures and training algorithms have been developed so far. Different aspects …

    missouri Repository record for Developing neural network applications using LabVIEW (opens in a new tab)

  8. Approximation of CPU code using neural networks

    … function compared to an equivalent CPU function. Neural nets are fairly general purpose tools which can perform pattern recognition or arithmetic operations on a block of input data and produce a corresponding block of output data. The aim of this project is to be able to select a fairly arbitrary …

    uiuc Repository record for Approximation of CPU code using neural networks (opens in a new tab)

  9. Interpretable Deep Image Denoiser by Unrolling Graph Laplacian Regularizer

    … minima. This thesis proposes an image denoising neural net constructed by unrolling an iterative algorithm solving a maximum a posteriori (MAP) optimization problem regularized using a graph Laplacian prior. To guarantee a minimum level of performance, we initialize the network to a known …

    york Repository record for Interpretable Deep Image Denoiser by Unrolling Graph Laplacian Regularizer (opens in a new tab)

  10. Global estimation of precipitation using opaque microwave bands

    … components whose outputs are fed into a neural net to produce a rain rate estimate for each 15-km spot. The signal processing components utilize techniques such as principal component analysis for characterizing groups of channels, spatial filtering for cloud-clearing brightness …

    mit Repository record for Global estimation of precipitation using opaque microwave bands (opens in a new tab)

  11. A flexible and innovative platform for autonomous mobile robots

    … framework to facilitate implementation of neural net architectures by users. The work described in this thesis includes a set of macros that expand the CREAL language to allow user-friendly creation of neural nets. This abstraction framework is then put into use in an implementation that …

    mit Repository record for A flexible and innovative platform for autonomous mobile robots (opens in a new tab)

  12. Applying Neural Networks for Tire Pressure Monitoring Systems

    … monitoring system is developed using neural net- works to identify the tire pressure of a vehicle tire. A quarter-car model was developed with Matlab and Simulink to generate simulated accelerometer output data. Simulation data are used to train and evaluate a recurrent neural network …

    calpoly Repository record for Applying Neural Networks for Tire Pressure Monitoring Systems (opens in a new tab)

  13. Investigating Aerosol Composition with Low Cost Optical Particle Counters

    … in concert with a simple fully connected neural net. Simulated effects of thermal denuders as well as dryers/humidifiers are used to perturb aerosols before they enter simulated low-cost optical particle counters (OPCs). This provides information on the volatility and hygroscopicity of the …

    mit Repository record for Investigating Aerosol Composition with Low Cost Optical Particle Counters (opens in a new tab)

  14. Applying Artificial Intelligence and Mobile Technologies to Enable Practical Screening for Diabetic Retinopathy

    … of an image processing pipeline and a neural net algorithm that automatically tests image quality (based on brightness, color, and amount of blur), rejects poor quality images, and re-formats each image into a standard image resolution. In order to create a generalized model, I used a …

    mit Repository record for Applying Artificial Intelligence and Mobile Technologies to Enable Practical Screening for Diabetic Retinopathy (opens in a new tab)

  15. Smarter NEAT Nets

    … to improve usability and functionality of a ge- netic neural net algorithm called NEAT (NeuroEvolution of Augmenting Topolo- gies). The modification aims to accomplish its goal by automatically changing parameters used by the algorithm with little input from a user. The advan- tage of the …

    calpoly Repository record for Smarter NEAT Nets (opens in a new tab)

  16. Text-Driven Movie Manipulation

    … method consisted of training a video-specific neural net model with an existing architecture for extracting keypoints, manipulating a representative frame to fit the user’s textual description through latent optimization, and producing a new video in a single forward pass. Our method requires …

    mit Repository record for Text-Driven Movie Manipulation (opens in a new tab)

  17. Modelling Outcomes in Canadian Professional Football via Generalized Bradley-Terry Models

    … (MM) algorithms and descriptions Artificial Neural Net- work (ANN) processes that can be leveraged to estimate such models' parameters. Various candidate models, parameterized by regular-season CFL game outcomes from 2004-2017, are performance-tested against post-season playoff game outcomes …

    regina Repository record for Modelling Outcomes in Canadian Professional Football via Generalized Bradley-Terry Models (opens in a new tab)

  18. 3D reconstruction of human body via machine learning

    … is composed of an end-to-end 3D reconstruction neural net with a skinned multi-person linear model (SMPL) model by the generative adversarial networks (GANs). The 3D facial reconstruction used the morphable facial model by principal component analysis (PCA) and the LS3D-W database. The 3D …

    mit Repository record for 3D reconstruction of human body via machine learning (opens in a new tab)

  19. Design and evaluation of a novel convolutional neural network for short-term vehicle multi-traffic prediction

    … In this thesis, we propose a convolutional neural net-work model that performs traffic forecasting for all three parameters, using historical integrated traffic data over a large area. The proposed model also predicts all three parameters for all 5-minute intervals from the initial time up …

    uoit Repository record for Design and evaluation of a novel convolutional neural network for short-term vehicle multi-traffic prediction (opens in a new tab)

  20. Simulating prediction markets that include human and automated agents

    … performance of these markets. I start with the neural net-based agent that is currently used in CCI's collective prediction experiments on football plays. By tuning their training and risk affinity, I configure a "smart" agent to represent the sophisticated computer traders. I implement three …

    mit Repository record for Simulating prediction markets that include human and automated agents (opens in a new tab)

Page 1 of 3