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 69 for “"MNIST"”.

  1. Understanding Adversarial Training: Improve Image Recognition Accuracy of Convolution Neural Network

    … and classify images in 4 types of data sets; MNIST (hand-writing digits), CIFAR10 (animal, food, vehicle pictures), MNIST and CIFAR10 adversarial example. The optimal performance on MNIST and CIFAR10 was achieved by using two essential steps. First, we created a basic convolutional neural …

    cuny Repository record for Understanding Adversarial Training: Improve Image Recognition Accuracy of Convolution Neural Network (opens in a new tab)

  2. An investigation of observed Algorithmic Specified Complexity.

    … compressibility of random bitstrings. The ASC of MNIST pictures was estimated by saving concatenations of samples as PNG. The expected ASC of random bitstrings was compared to average observed ASC (OASC) values from LZ78 Huffman codes. Observed ASC of MNIST pictures helped to identify them, and as …

    baylor Repository record for An investigation of observed Algorithmic Specified Complexity. (opens in a new tab)

  3. A Full System Co-Simulation Platform for Evaluating Edge Machine Learning Inference Using Compute-in-Memory

    … To evaluate performance, we benchmark an MNIST image inference workload and a synthetic fully connected neural network, comparing CPU-only execution with CIM-offloaded execution. For MNIST, CIM reduces CPU instruction count by 88.6% and estimated total system dynamic energy by 84.0%. …

    chapman Repository record for A Full System Co-Simulation Platform for Evaluating Edge Machine Learning Inference Using Compute-in-Memory (opens in a new tab)

  4. Resource and data optimization for hardware implementation of deep neural networks targeting FPGA-based edge devices

    … of 175.7 μs for classifying one image in the MNIST data set using the LeNet and 653.5 μs for classifying one image in the Cifar-10 data set using the CifarNet. For the LeNet we were able to maintain high accuracy of 97.6% for the MNIST data set and 83.4% for the Cifar-10 data set. We achieved …

    uiuc Repository record for Resource and data optimization for hardware implementation of deep neural networks targeting FPGA-based edge devices (opens in a new tab)

  5. Simulating an Optical Neural Network for Deep Learning in Edge Computing

    … on two real-world machine vision applications: MNIST digit classification and scene recognition. The netcast ONN enables large DNNs to run on SWaP-limited edge devices with significantly less energy needed to run inference compared to digital models. Software simulations are used to assess …

    mit Repository record for Simulating an Optical Neural Network for Deep Learning in Edge Computing (opens in a new tab)

  6. The Future of Computing: An Energy-Efficient In-Memory Computing Architectures with Emerging VGSOT MRAM Technology

    … in performance evaluations conducted using the MNIST and FMNIST datasets with a BNN model structured as 512-512-10 (input layer - hidden layer - output layer), the proposed VGSOT MRAM demonstrates exceptional inference accuracy. Specifically, it achieves a high accuracy rate of 97.40% for the …

    vt Repository record for The Future of Computing: An Energy-Efficient In-Memory Computing Architectures with Emerging VGSOT MRAM Technology (opens in a new tab)

  7. 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)

  8. Large-Scale Optical Hardware for Neural Network Inference Acceleration

    … Our experimental implementation showed an MNIST classification accuracy within <0.6% of the digital electronic ground truth. We estimated that this 'digital ONN' could reduce energy consumption for long data transfer lengths, but not in tightly packed electronic multiplier arrays. …

    mit Repository record for Large-Scale Optical Hardware for Neural Network Inference Acceleration (opens in a new tab)

  9. Provable stability defenses for targeted data poisoning

    … attacks. Empirically, we report findings on the MNIST 1-7 image classification dataset and the TREC 2007 spam detection dataset that confirms our theoretical findings.

    uiuc Repository record for Provable stability defenses for targeted data poisoning (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. Benefits of branches in sparsely connected networks

    … from fault. Under image classification tasks (MNIST & FashionMNIST), it was found that branching granted benefits to sparse BCNs in terms of performance and ability to recover from fault. An “output connectedness” notion, useful for analyzing sparse networks, is defined. To conclude, this work …

    mit Repository record for Benefits of branches in sparsely connected networks (opens in a new tab)

  12. Recognition and verification of unconstrained handwritten numerals

    … synthesized by morphing. CENPARMI database and MNIST database are used for evaluation. UTHN recognition is an important component for automatic document processing in applications such as cheque processing. However, it is a more difficult problem that has attained less attention, reflected by …

    concordia Repository record for Recognition and verification of unconstrained handwritten numerals (opens in a new tab)

  13. A Deep Learning and Signal Processing Architecture Using Frequency-Encoded RF Photonics

    … demonstrate a 3-layer DNN for inference of MNIST digits, showing a scalable, fully analog front-to-end ONN. This architecture is also the first deep neural network hardware accelerator that is suited for direct inference of time-based signals without digitization.

    mit Repository record for A Deep Learning and Signal Processing Architecture Using Frequency-Encoded RF Photonics (opens in a new tab)

  14. Explanation Alignment: Quantifying the Correctness of Model Reasoning At Scale

    … models, multiple saliency methods, and MNIST, CelebA, and ImageNet tasks, we find that explanation alignment automatically identifies spurious correlations, such as model bias, and uncovers behavioral differences between nearly identical models. Further, we characterize the relationship …

    mit Repository record for Explanation Alignment: Quantifying the Correctness of Model Reasoning At Scale (opens in a new tab)

  15. Enhanced Neural Network Training Using Selective Backpropagation and Forward Propagation

    … This thesis tests these new algorithms on the MNIST and CASIA datasets, and achieves successful results with both algorithms on the two datasets. The selective backpropagation algorithm shows a reduction of up to 93.3% of backpropagations completed, and the selective forward propagation …

    vt Repository record for Enhanced Neural Network Training Using Selective Backpropagation and Forward Propagation (opens in a new tab)

  16. A Method for Image Classification Using Low-Precision Analog Computing Arrays

    … and tested with two benchmark problems (MNIST hand-written digits and traffic signs). Software simulations evaluate the methods under various defined computation faults. A model-free closed-loop technique is shown to compensate for rather serious computation errors without the need for …

    heid-diss Repository record for A Method for Image Classification Using Low-Precision Analog Computing Arrays (opens in a new tab)

  17. 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)

  18. Deep generative models via explicit Wasserstein minimization

    … on the training and testing sets of the MNIST and Thin-8 data. As a side product, the thesis proposes several effective metrics of measure performance of deep generative models. The thesis closes with a discussion of the unsuitability of the Wasserstein distance for certain tasks, as has …

    uiuc Repository record for Deep generative models via explicit Wasserstein minimization (opens in a new tab)

  19. Modeling Integrated Cortical Learning: Explorations of Cortical Map Development, Unit Selectivity, and Object Recognition

    … on two image recognition benchmarks (Fashion-MNIST & ImageNette). These simulation studies showed three main results. First, that the ICL model developed continuous topological maps in its upper layers, but these maps were not substantially different from the maps developed in its lower layers …

    tdl Repository record for Modeling Integrated Cortical Learning: Explorations of Cortical Map Development, Unit Selectivity, and Object Recognition (opens in a new tab)

  20. Classification with noisy labels : "Multiple Account" cheating detection in Open Online Courses

    … rate estimation and F1, error, and AUC-PR on the MNIST and CIFAR datasets, regardless of noise rates. To highlight, Rank Pruning with a CNN classifier can predict if a MNIST digit is a one or not one with only 0:25% error, and 0:46% error across all digits, even when 50% of positive examples are …

    mit Repository record for Classification with noisy labels : "Multiple Account" cheating detection in Open Online Courses (opens in a new tab)

Page 1 of 4