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 17 of 17 for “"Alexnet"”.

  1. FEASIBILITY OF DETECTING AND CLASSIFYING SMALL UNMANNED AERIAL SYSTEM THREATS USING ACOUSTIC DATA

    … The pre-trained convolutional neural network, AlexNet, was used as the method for detecting UAS. Acoustic data was collected in a variety of conditions and converted to a JPEG representation of the continuous wavelet transform. Then the data was used to train and evaluate the performance of …

    nps Repository record for FEASIBILITY OF DETECTING AND CLASSIFYING SMALL UNMANNED AERIAL SYSTEM THREATS USING ACOUSTIC DATA (opens in a new tab)

  2. A Deep Learning Pipeline for Classifying Different Stages of Alzheimer's Disease from fMRI Data.

    … convolutional neuronal network architecture AlexNet was applied to fMRI datasets to classify different stages of the disease. We classified five different stages of Alzheimer’s using a deep learning algorithm. The method successfully classified normal healthy control (NC), significant memory …

    brock Repository record for A Deep Learning Pipeline for Classifying Different Stages of Alzheimer's Disease from fMRI Data. (opens in a new tab)

  3. RF Fingerprinting Unmanned Aerial Vehicles

    … the identity of each UAV. To achieve this goal, AlexNet with the data augmentation technique was employed.</p>

    embry-riddle Repository record for RF Fingerprinting Unmanned Aerial Vehicles (opens in a new tab)

  4. Efficientnext: Efficientnet For Embedded Systems

    … Neural Networks have come a long way since AlexNet. Each year the limits of the state of the art are being pushed to new levels. EfficientNet pushed the performance metrics to a new high and EfficientNetV2 even more so. Even so, architectures for mobile applications can benefit from improved …

    iupui Repository record for Efficientnext: Efficientnet For Embedded Systems (opens in a new tab)

  5. Detecção de instrumentos musicais com redes neurais profundas

    … famosas utilizadas para a classificação (LeNet, AlexNet e GoogLeNet) e suas devidas arquiteturas e tarefas originais. Confrontamos as redes treinadas com diferentes conjuntos de dados gerados a partir de espectrogramas variando os parâmetros de tempo (100ms e 500ms) e escala de cor da potência do …

    brazil-uff Repository record for Detecção de instrumentos musicais com redes neurais profundas (opens in a new tab)

  6. Investigation on ImageNet Remaining Errors with TRAK

    … motivated the breakthrough deep learning model Alexnet a decade ago. As researches progress and computation power grows, the best models nowadays can achieve accuracy as high as 90% on Imagenet. With such high accuracy, model predictions are usually of high precision and the causes of this long …

    mit Repository record for Investigation on ImageNet Remaining Errors with TRAK (opens in a new tab)

  7. Comparing the Performance of Small Word-Size Floating-Point Numerics to Fixed-Point Numerics in Neural Networks

    … implemented in software and evaluated using an AlexNet-style model on the SVHN dataset. The experiments compare three training configurations: a fixed-point baseline, adaptive floating-point quantization, and adaptive quantization with bit-shuffling. Results show that the APT models achieve …

    gatech Repository record for Comparing the Performance of Small Word-Size Floating-Point Numerics to Fixed-Point Numerics in Neural Networks (opens in a new tab)

  8. Efficient ML Inference via Matrix-Vector Approximations

    … evaluations across two representative models, AlexNet on CIFAR10 and DistilBERT on AG News, comparing quantization, sparsification, and low-rank approximations. Our analysis spans four perspectives: (1) how different methods trade off ℓ₂ error and compression, (2) how weight statistics and …

    mit Repository record for Efficient ML Inference via Matrix-Vector Approximations (opens in a new tab)

  9. Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks

    … (MNIST dataset), LeNet-5 (MNIST dataset), AlexNet (CIFAR-10 dataset) and VGG-16 (CIFAR-10 dataset), post-training quantization achieves 7.62x, 10.87x, 6.39x and 12.43x compression, in-training quantization achieves 22.08x, 21.05x, 7.95x and 12.71x compression and combined quantization …

    vt Repository record for Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks (opens in a new tab)

  10. Architecture design for highly flexible and energy-efficient deep neural network accelerators

    … 278 mW at 34.7 fps for the CONV layers of AlexNet, which is 10x more efficient than a mobile GPU. Eyeriss v2 addresses support for the emerging compact DNNs that introduce higher variation in data reuse. It features a RS+ dataflow that improves PE utilization, and a flexible and scalable …

    mit Repository record for Architecture design for highly flexible and energy-efficient deep neural network accelerators (opens in a new tab)

  11. Algorithms and low power hardware for keyword spotting

    … at complex tasks using large CNN models, e.g. AlexNet, or support limited neural network (NN) architectures which delivers lower classification accuracy for KWS. This thesis takes an algorithm-and-hardware co-design approach to implement a low power NN accelerator for the KWS system that is …

    mit Repository record for Algorithms and low power hardware for keyword spotting (opens in a new tab)

  12. Automatic Registration of Imagery to Mobile LiDAR Maps

    … in two disparate image sets. The fourth layer of AlexNet was found to provide the most ideal feature descriptor for registration between RCIs and SCIs. The approximate location of the RCI using SCIs as interpreters between RCI and MMS point-cloud detect scenes at a precision of 97% when changes …

    calgary Repository record for Automatic Registration of Imagery to Mobile LiDAR Maps (opens in a new tab)

  13. Near-Memory Processing for Low-precision Deep Neural Networks

    … constraints. An evaluation using a BCNN based on AlexNet indicates that for mode S, a configuration of one hardware replica with 16 filters per replica offers an optimal balance between area, runtime, and energy. In contrast, for mode T, the best configuration comprises 16 replicas and 32 filters. …

    cambridge Repository record for Near-Memory Processing for Low-precision Deep Neural Networks (opens in a new tab)

  14. Automatic feature extraction for time series analysis using deep and machine learning

    … pre-trained convolutional neural networks (AlexNet and GoogLeNet) as classifiers is proposed, achieving a significant val- idation accuracy of 98.08% for distinguishing between fall and no-fall scenarios in the first model. The signals are pre-processed to reduce noise, and frequency-time …

    cadiz Repository record for Automatic feature extraction for time series analysis using deep and machine learning (opens in a new tab)

  15. Efficient Image and Video Representations for Retrieval

    … layer of a popular convolutional Neural Network (AlexNet) with the class binary codes and show that the hashing functions learned in this way outperforms the state­ of ­the art, and at the same time provide fast retrieval times. In the second part, we also address the problem of supervised …

    maryland Repository record for Efficient Image and Video Representations for Retrieval (opens in a new tab)

  16. Person of interest rapid identification and tracking (POIRIT) assistance system

    … research employs transfer learning models like AlexNet, GoogLeNet, ResNet, and VGG-Face, ultimately determining the most effective model for each classification layer. For gender classification, VGG Face exhibits the best performance with an accuracy of 98.41%, which is 1% more than the best …

    cape-town Repository record for Person of interest rapid identification and tracking (POIRIT) assistance system (opens in a new tab)

  17. Parameter reduction in deep learning and classification

    The goal of this thesis is to develop methods to reduce model and problem complexity in the area of classification tasks. Whether it is a traditional or a deep learning classification task, decreasing complexity helps to greatly improve efficiency, and also adds regularization to the models. In …

    cork Repository record for Parameter reduction in deep learning and classification (opens in a new tab)