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 73 for “"MNIST dataset"”.

  1. Common Source Amplifier Based Machine Learning Assisted Image Classification

    … accuracy of 0.82 is achieved on the MNIST dataset which consists of handwritten images of digits from 0-9. Use of common-source amplifier structure simplifies the ANN and results in 5X lower energy consumption than existing analog classifiers. The classifier performance is validated …

    buffalo Repository record for Common Source Amplifier Based Machine Learning Assisted Image Classification (opens in a new tab)

  2. Scalable Digital Architecture of Hierarchical Temporal Memory Spatial Pooler

    … pooler design is evaluated against the standard MNIST dataset, obtaining up to 90% and 88% classication accuracy for the train and test data, respectively. Additionally, the designs are tested on the MNIST dataset, in the presence of noise, to determine its robustness. Fluctuations of up to 10% …

    rit Repository record for Scalable Digital Architecture of Hierarchical Temporal Memory Spatial Pooler (opens in a new tab)

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

    … for sparse matrix storage. On LeNet-300-100 (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 …

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

  4. Experiments on the Neural Network Approach to the Handwritten Digit Classification Problem

    When the MNIST dataset was introduced in 1998, training a network was a multiple week problem in order to receive results far less accurate than an average CPU can produce within a couple of hours today. While this indicates that training a network on such a dataset is not the complicated problem …

    gsu Repository record for Experiments on the Neural Network Approach to the Handwritten Digit Classification Problem (opens in a new tab)

  5. Design of Reversible Quantum Logic Structures in CMOS Technology

    … Functionality was carried out by processing the MNIST Dataset, a handwritten digit database for number recognition.

    rit Repository record for Design of Reversible Quantum Logic Structures in CMOS Technology (opens in a new tab)

  6. DNN Weight Compression Method with ADMM Framework

    … is training on the LeNet-5 model using the MNIST dataset and has 222.3x weight number reduction as the result.

    tamu Repository record for DNN Weight Compression Method with ADMM Framework (opens in a new tab)

  7. An Analysis of Heterogeneous Quantization Schemes for Neural Networks

    … perceptron (MLP)—were studied with the MNIST and CIFAR-10 image classification datasets. The weights of the models were quantized during training using the deterministic rounding technique. The models were either quantized homogeneously, with all weights quantized to the same precision, …

    rit Repository record for An Analysis of Heterogeneous Quantization Schemes for Neural Networks (opens in a new tab)

  8. Deep Learning Approaches for Predicting Strain Energy in Heterogeneous Materials

    … materials. Utilizing the Mechanical MNIST dataset, comprising 60,000 simulated samples of 28x28 pixel domains under large deformation, the study evaluates classical regression methods (Linear Regression, Random Forest, Gradient Boosting) and advanced deep learning architectures …

    sdstate Repository record for Deep Learning Approaches for Predicting Strain Energy in Heterogeneous Materials (opens in a new tab)

  9. A Continuous Space Generative Model

    … presents results obtained by training on the MNIST dataset of handwritten digits to validate the method, and it elaborates on the potential applications for continuous generative models.

    arkansas Repository record for A Continuous Space Generative Model (opens in a new tab)

  10. Analytical guarantees for reduced precision fixed-point margin hyperplane classifiers

    … and applied to the `two vs. four' task of the MNIST dataset is ~2x more accurate than a standard 8 bit low-precision implementation in spite of using ~2x10^4 fewer 1 bit full adders and ~2x10^3 fewer bits for data and weight representation.

    uiuc Repository record for Analytical guarantees for reduced precision fixed-point margin hyperplane classifiers (opens in a new tab)

  11. Kvantinių skaičiavimų ir algoritmų tyrimas naudojant simuliatorių paprastame personaliniame kompiuteryje /

    … layer for preprocessing images of CIFAR­10 dataset was constructed. The output of this layer is used as input for a simple neural network. Also, a hybird model using Grover’s algorithm is created and adapted to perform multi­class sinlge­label classification on the MNIST dataset. The …

    vilnius Repository record for Kvantinių skaičiavimų ir algoritmų tyrimas naudojant simuliatorių paprastame personaliniame kompiuteryje / (opens in a new tab)

  12. Realization of Multi-Valued Logic Using Optical Quantum Computing

    … data quantum classifier on ten classes of the MNIST dataset. In this dissertation, I provide the background information of optical quantum computing as an ideal candidate material for building the future classical-quantum hybrid internet for its numerous benefits, among which the compatibility …

    portland-state Repository record for Realization of Multi-Valued Logic Using Optical Quantum Computing (opens in a new tab)

  13. Neuromorphic Ensemble Workflow

    … crafted by the NEW and evaluate it on the MNIST dataset against multiclass SNN baselines trained under identical conditions. The best NEW configuration achieves 0.9042 accuracy compared to 0.3347 for the multiclass baseline, an improvement of over 57 percentage points, while introducing a …

    ut-knoxville Repository record for Neuromorphic Ensemble Workflow (opens in a new tab)

  14. Data generalization for new classes with a single instance via automatic style labeling and transfer

    … but also exhibit variety. Experiments on the MNIST dataset show that after hiding away one class of digits and training only on the data of the remaining nine classes, our model can successfully generate new images of the hidden class with controllable features, given just a single image from …

    uiuc Repository record for Data generalization for new classes with a single instance via automatic style labeling and transfer (opens in a new tab)

  15. All-digital time-domain CNN engine for energy efficient edge computing

    … of this work implements LeNet-5 CNN to classify MNIST dataset (handwritten digits) and is demonstrated on a commercial 40nm CMOS Test-chip. Phase II of this work aims to scale-up this work for multi-bit weights and implements AlexNet CNN to classify 1000-class ImageNet dataset images

    texas Repository record for All-digital time-domain CNN engine for energy efficient edge computing (opens in a new tab)

  16. Exploring efficient Federated Learning via Graph Signal Processing

    … sample clients during model training. We use the MNIST dataset, and we show that even when only a subset of similar clients is sampled and used in training, we can achieve comparable, if not similar, results. We select clients based on cosine similarity score, motivated by the idea that updates …

    ttu Repository record for Exploring efficient Federated Learning via Graph Signal Processing (opens in a new tab)

  17. Research on fashion classifier algorithms /

    … fashion classification using the Fashion-MNIST dataset. The study evaluates eight model configurations across five architectures: LeNet-5, AlexNet, ResNet-18, EfficientNet-B0, and Vision Transformer (ViT-B/16), comparing both models trained from scratch and those utilizing transfer …

    vilnius Repository record for Research on fashion classifier algorithms / (opens in a new tab)

  18. A Scalable Flash-Based Hardware Architecture for the Hierarchical Temporal Memory Spatial Pooler

    … model of the hardware is evaluated against the MNIST dataset, yielding 91.98% classification accuracy. A fully custom layout is developed to validate the design in a TSMC 180nm process. The area and power footprints of the spatial pooler are 30.538mm2 and 5.171mW, respectively. Storage processor …

    rit Repository record for A Scalable Flash-Based Hardware Architecture for the Hierarchical Temporal Memory Spatial Pooler (opens in a new tab)

  19. Nearest neighbor classification using a density sensitive distance measurement [electronic resource]

    … takes into account the density of an underlying dataset to better represent the shape of the data when measuring distance. Kernel density estimation, using kernel bandwidths determined by k -nearest neighbor distances, is used to approximate the density of the underlying dataset. A scale is …

    nps Repository record for Nearest neighbor classification using a density sensitive distance measurement [electronic resource] (opens in a new tab)

Page 1 of 4