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 88 for “"BNN"”.

  1. Νευροπροστατευτική και αντιφλεγμονώδης δράση της συνθετικής μικρονευροτροφίνης BNN-20 στο μοντέλο προοδευτικής ντοπαμινεργικής νευροεκφύλισης μυός "weaver"

    BNN-20 is a synthetic microneurotrophin, long-term administration (P1-P21) of which exerts potent neuroprotective effect on the “weaver” mouse, a genetic model of progressive, nigrostriatal dopaminergic degeneration. The present study provides evidence that BNN-20 fully protects the dopaminergic …

    greece Repository record for Νευροπροστατευτική και αντιφλεγμονώδης δράση της συνθετικής μικρονευροτροφίνης BNN-20 στο μοντέλο προοδευτικής ντοπαμινεργικής νευροεκφύλισης μυός "weaver" (opens in a new tab)

  2. Neuronale Netze als Modell Boolescher Funktionen

    … eine neue Art von Booleschen Neuronalen Netzen (BNN) entwickelt. Das Basiselement Boolescher Neuronaler Netze ist ein neuartiges Boolesches Neuron (BN), das im Gegensatz zum klassischen Neuron direkt mit Booleschen Signalen operiert und dafür ausschließlich Boolesche Operationen benutzt. Für das …

    qucosa-diss

  3. Back-propagation neural networks in adaptive control of unknown nonlinear systems

    … is to develop a Back-propagation Neural Network (BNN) to control certain classes of unknown nonlinear systems and explore the network's capabilities. The structure of the Direct Model Reference Adaptive Controller (DMRAC) for Linear Time Invariant (LTI) systems with unknown parameters is first …

    nps Repository record for Back-propagation neural networks in adaptive control of unknown nonlinear systems (opens in a new tab)

  4. Performance Comparison of Binarized Neural Network with Convolutional Neural Network

    … used in deep learning. Binarized Neural Network (BNN) is also a neural network which consists of binary weights and activations. Neural Networks has large number of parameters and overfitting is a common problem to these networks. To overcome the overfitting problem, dropout is a solution. …

    mtu Repository record for Performance Comparison of Binarized Neural Network with Convolutional Neural Network (opens in a new tab)

  5. The Role of Charge-Transfer Interactions and Delocalization in Annelated Nitronyl Nitroxides

    … a series of annelated benzonitronyl nitroxide (BNN) radicals. The BNN radicals exhibited remarkably low reduction potentials (~0.0 V vs SCE) and a near-infrared absorption attributed to a HOMO–SOMO charge-transfer excitation. The annelated BNN radicals were found to be less stable than the …

    uvic Repository record for The Role of Charge-Transfer Interactions and Delocalization in Annelated Nitronyl Nitroxides (opens in a new tab)

  6. Exploring FPGA Implementation for Binarized Neural Network Inference

    … works have shown the binarized neural networks (BNN), utilizing binarized (i.e. +1 and -1) convolution kernel and binarized activation function, can significantly reduce the parameter size and computation cost, which makes it hardware-friendly for Field-Programmable Gate Arrays (FPGAs) …

    ucf Repository record for Exploring FPGA Implementation for Binarized Neural Network Inference (opens in a new tab)

  7. Back-propagation neural networks in adaptive control of unknown nonlinear systems

    … is to develop a Back-Propagation Neural Network (BNN) to control certain classes of unknown nonlinear systems and explore the network's capabilities. The structure of the Direct Model Reference Adaptive Controller (DMRAC) for Linear Time Invariant (LTI) systems with unknown parameters is first …

    nps Repository record for Back-propagation neural networks in adaptive control of unknown nonlinear systems (opens in a new tab)

  8. Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies

    … As a key example, Bayesian Neural Networks (BNNs) are one of the most successful Bayesian models being increasingly employed in a wide range of real-world AI applications which demand reliable and robust decisions. However, the nature of BNN stochastic inference and training procedures incurs …

    houston Repository record for Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies (opens in a new tab)

  9. Binary Neural Networks in Spintronic Memory

    … commercial significance. Binary neural networks (BNN) are particularly effective in trading accuracy for performance, energy efficiency or hardware/software complexity. In this thesis, I demonstrate a spintronic, re-configurable in-memory BNN accelerator, affectionately named PIMBALL: Processing …

    umn Repository record for Binary Neural Networks in Spintronic Memory (opens in a new tab)

  10. Nonlinear adaptive control using backpropagating neural networks

    … system using backpropagating neural networks (BNN's) in conjunction with a linear quadratic regulator (LQR). the basic concepts of adaptive control and the structure of neural networks are discussed. These concepts are integrated and the nonlinear regulator is derived. Simulation is conducted …

    nps Repository record for Nonlinear adaptive control using backpropagating neural networks (opens in a new tab)

  11. Application of a back-propagation neural network to isolated-word speech recognition

    … explore how a back- propagation neural network (BNN) can be applied to isolated-word speech recognition. Simulation results show that a BNN provides an effective approach for small vocabulary systems. The recognition rate reaches 100% for a 5-word system and 94% for a 10-word system. The general …

    nps Repository record for Application of a back-propagation neural network to isolated-word speech recognition (opens in a new tab)

  12. Investigation of the potential neuroprotective role of a BDNF analog in Parkinson's disease patient-derived neurons

    … και μη κινητικά συμπτώματα. Η μικρονευροτροφίνη BNN-20 είναι μια συνθετική ένωση που μιμείται τον νευροτροφικό παράγοντα BDNF και παρουσιάζει πλειοτροπική νευροπροστατευτική επίδραση στους ντοπαμινεργικούς νευρώνες της μέλαινας ουσίας του παρκινσονικού ζωικού μοντέλου "weaver". Στη μελέτη αυτή …

    athens Repository record for Investigation of the potential neuroprotective role of a BDNF analog in Parkinson's disease patient-derived neurons (opens in a new tab)

  13. Accelerating biophysical neural network simulation with region of interest based approximation

    … the dynamics of biophysical neural network (BNN) is essential to understand brain operation and design cognitive systems. Large-scale and biophysically plausible BNN modeling requires solving multiple-terms, coupled and non-linear differential equations, making simulation computationally …

    gatech Repository record for Accelerating biophysical neural network simulation with region of interest based approximation (opens in a new tab)

  14. FPGA-based Additive Manufacturing Defects Detection and Optimization of Smart Connected Devices

    … of defects. Experiments show that the BNN model on NEU-DET can achieve 97.9% accuracy in identifying whether the image is defective or defect-free. The FPGA-based BNN module can process one image within 0.5 s. The BNN design is modularized and can be duplicated in parallel to fully …

    houston Repository record for FPGA-based Additive Manufacturing Defects Detection and Optimization of Smart Connected Devices (opens in a new tab)

  15. Triatominae in North America : a comparison of statistical machine learning approaches for habitat suitability modelling

    … model [BLR], and a Bayesian Neural Network [BNN] adapted to model both joint, and single species distributions. It was found that the single species models perform well outside of the observed range of predictor variables, MaxEnt AUC > 0.9 and BNN had a fraction of correct predictions on test …

    texas Repository record for Triatominae in North America : a comparison of statistical machine learning approaches for habitat suitability modelling (opens in a new tab)

  16. Improving Visual Place Recognition in Changing Environments

    … feature descriptors to Binary Neural Networks (BNN), to improve the computational and energy efficiency of VPR. The best BNN-based VPR descriptor obtained runs up to one order of magnitude faster than many CNN-based and hand-crafted approaches while maintaining comparable performance and …

    essex Download PDF for Improving Visual Place Recognition in Changing Environments (opens in a new tab)

  17. Bayesian Framework for Aleatoric and Epistemic Uncertainty Quantification of Quantitative Parameters: Application to DCE-MRI of the Liver

    … model); ii) Training of Bayesian Neural network (BNN) using the simulated data; and iii) Inference of the parameters and uncertainties by application of in-vivo DCE-MR images. The images were acquired for five male patients (56±8 years and, 88±11kg) with hepatic metastases. The estimated …

    fu-berlin Repository record for Bayesian Framework for Aleatoric and Epistemic Uncertainty Quantification of Quantitative Parameters: Application to DCE-MRI of the Liver (opens in a new tab)

  18. Comparison of linearly and nonlinearly statistically downscaled atmospheric variables in terms of future climate indices and daily variability

    … learning models (e.g. Bayesian neural network (BNN), adaptive regression sufficiently smooth polynomials, and classification and regression trees (CART)) and multiple linear regression models were used to downscale the Canadian Global Climate Model 3.1 output using the Canadian Regional Climate …

    ubc Repository record for Comparison of linearly and nonlinearly statistically downscaled atmospheric variables in terms of future climate indices and daily variability (opens in a new tab) Download PDF for Comparison of linearly and nonlinearly statistically downscaled atmospheric variables in terms of future climate indices and daily variability (opens in a new tab)

  19. Short lead-time streamflow forecasting by machine learning methods, with climate variability incorporated

    … process (GP), and Bayesian neural network (BNN) models, and the results are compared with the multiple linear regression (MLR) model. Lead-time for forecasting varies from 1 to 7 days. This study has been applied to a small coastal watershed in British Columbia, Canada. Model comparisons …

    ubc Repository record for Short lead-time streamflow forecasting by machine learning methods, with climate variability incorporated (opens in a new tab) Download PDF for Short lead-time streamflow forecasting by machine learning methods, with climate variability incorporated (opens in a new tab)

Page 1 of 5