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 121 for “"Convolutional Neural Networks (CNNs)"”.

  1. Deep Structured Multi-Task Learning for Computer Vision in Autonomous Driving

    … currently dominated by deep learning advances. Convolutional Neural Networks (CNNs) have become the predominant tool for solving almost any computer vision task, so state-of-the-art systems have been built by using the predictive capabilities of Convolutional Neural Networks (CNNs). Many of …

    cambridge Repository record for Deep Structured Multi-Task Learning for Computer Vision in Autonomous Driving (opens in a new tab)

  2. Visual tasks beyond categorization for training convolutional neural networks

    … category. In this paper, we explore- whether convolutional neural networks (CNNs) can also learn object-related variables. The models are trained for object position, size and pose, respectively, from synthetic images and tested on unseen held-out objects. First, we show that some object …

    mit Repository record for Visual tasks beyond categorization for training convolutional neural networks (opens in a new tab)

  3. A deep convolutional neural network approach for biomedical applications.

    … subset of machine learning that uses multi layer neural networks to perform desired tasks by using trained models. Neural networks are nonlinear mapping systems whose structure and function are loosely modeled on the physical structure of the nervous systems in humans and animals. In deep …

    baylor Repository record for A deep convolutional neural network approach for biomedical applications. (opens in a new tab)

  4. Neural Network Pruning for ECG Arrhythmia Classification

    <p>Convolutional Neural Networks (CNNs) are a widely accepted means of solving complex classification and detection problems in imaging and speech. However, problem complexity often leads to considerable increases in computation and parameter storage costs. Many successful attempts have been made …

    calpoly Repository record for Neural Network Pruning for ECG Arrhythmia Classification (opens in a new tab)

  5. Galaxy classification with deep convolutional neural networks

    … images are not suitable for galaxy images. Deep convolutional neural networks (CNNs) are able to learn powerful features from images by hierarchical convolutional and pooling operations. This work applies state-of-the-art deep CNN technologies to galaxy classification for both a regression task …

    uiuc Repository record for Galaxy classification with deep convolutional neural networks (opens in a new tab)

  6. Measuring and modifying the intrinsic memorability of images

    … appeal, etc.) in an image make it memorable. Convolutional neural networks (CNNs) trained on the data could predict an image's relative memorability with high accuracy. CNNs could also generate memorability heat maps which pinpoint which parts of an image are memorable. Finally, with …

    mit Repository record for Measuring and modifying the intrinsic memorability of images (opens in a new tab)

  7. Efficient fixed-radius near neighbors for machine learning

    … toward feature learning and better performance. Convolutional neural networks (CNNs) have especially demonstrated super-human performance in many vision tasks. One big reason for the success of CNNs is due to the use of parallelizable software and hardware to run these models, making their use …

    mit Repository record for Efficient fixed-radius near neighbors for machine learning (opens in a new tab)

  8. Benchmarking convolutional neural networks for object segmentation and pose estimation

    Convolutional neural networks (CNNs), particularly those designed for object segmentation and pose estimation, are now applied to robotics applications involving mobile manipulation. For these robotic applications to be successful, robust and accurate performance from the CNNs is critical. …

    mit Repository record for Benchmarking convolutional neural networks for object segmentation and pose estimation (opens in a new tab)

  9. Efficient Intelligence Towards Real-Time Precision Medicine With Systematic Pruning and Quantization

    The widespread adoption of Convolutional Neural Networks (CNNs) in real-world applications, particularly on resource-constrained devices, is hindered by their computational complexity and memory requirements. This research investigates the application of pruning and quantization techniques to …

    iupui Repository record for Efficient Intelligence Towards Real-Time Precision Medicine With Systematic Pruning and Quantization (opens in a new tab)

  10. Identifying facial landmarks, action units and emotions using deep networks

    The goal of this thesis it to use deep neural networks, specifically Convolutional Neural Networks (CNNs) to predict facial landmarks, facial action units and emotions and to study the results of intermediate experiments while doing so. Learning the different features of facial images has always …

    uiuc Repository record for Identifying facial landmarks, action units and emotions using deep networks (opens in a new tab)

  11. Neural geolocation prediction in Twitter

    … language processing, we study the application of neural models to the problem of geolocation prediction and experiment with multiple techniques to analyze neural networks for geolocation inference based solely on text. Experimental results on the dataset suggest that choosing appropriate network …

    uiuc Repository record for Neural geolocation prediction in Twitter (opens in a new tab)

  12. Sensorless ultrasound probe 6DoF pose estimation through the use of CNNs on image data

    … computationally costly. We explore the use of Convolutional Neural Networks (CNNs) to provide sensorless pose estimation. The Ultrasound CNN model proposed in this paper learns to regress the six degree of freedom (6-DoF) camera pose from a single ultrasound image in an end-to-end manner. …

    mit Repository record for Sensorless ultrasound probe 6DoF pose estimation through the use of CNNs on image data (opens in a new tab)

  13. Tardigrade: A Hardware Accelerator for Sparse Matrix Multiplication and Sparse Convolution

    … that of Gamma and recent accelerators for sparse convolutional neural networks (CNNs). Tardigrade shows comparable performance on SpMSpM and achieves a gmean 3.1× improvement in speed on sparse convolution.

    mit Repository record for Tardigrade: A Hardware Accelerator for Sparse Matrix Multiplication and Sparse Convolution (opens in a new tab)

  14. OFDM Channel Estimation with Artificial Neural Networks

    … investigates the application of artificial neural networks (ANNs) as a means of improving existing channel estimation techniques. Multi-layer feed forward neural networks (FNNs) and convolutional neural networks (CNNs) are tested on a variety of random fading channels with different …

    calpoly Repository record for OFDM Channel Estimation with Artificial Neural Networks (opens in a new tab)

  15. On the performance of convolutional neural networks initialized with Gabor filters.

    … popularity due to its various possible usages. Convolutional Neural Networks (CNNs) have been the classic approach taken on by many researchers because of their capability to learn through the parameter space given a sufficient amount of representative data. When observing a fully trained CNN, …

    baylor Repository record for On the performance of convolutional neural networks initialized with Gabor filters. (opens in a new tab)

  16. Frequency-domain deconvolution in deep learning

    … Recognizing the unparalleled success of convolutional neural networks (CNNs) in the realm of computer vision, we critically evaluate the performance and computational demands of traditional convolution operations against the proposed deconvolution method. Using a systematic approach, we …

    cape-town Repository record for Frequency-domain deconvolution in deep learning (opens in a new tab)

  17. Computer Vision Techniques for Drill Bit Identification and Mechanical Wear Detection

    … is demonstrated. Then, transfer learning of convolutional neural networks (CNNs) is applied to the same tasks, allowing comparison of results. This thesis also explores a means of presenting processed image outputs to non-technical operators in order to assist manual analysis of drill bit …

    mit Repository record for Computer Vision Techniques for Drill Bit Identification and Mechanical Wear Detection (opens in a new tab)

  18. Prospects for Quantum Equivariant Neural Networks

    Convolutional neural networks (CNNs) exploit translational invariance within images. Group equivariant neural networks comprise a natural generalization of convolutional neural networks by exploiting other symmetries arising through different group actions. Informally, a linear map is equivariant …

    mit Repository record for Prospects for Quantum Equivariant Neural Networks (opens in a new tab)

  19. Polar Region Sea Ice Classification With Multimodal Learning

    … a multimodal deep learning technique from a convolutional neural networks (CNNs) for polar image data and a RNN architecture for text data fusion, allowing the model to learn from multiple data modalities effectively. The experimental results demonstrate that the multimodal approach …

    tdl Repository record for Polar Region Sea Ice Classification With Multimodal Learning (opens in a new tab)

  20. Transformation-invariance properties of Grad-CAM in Convolutional Neural Networks

    The widespread adoption of Convolutional Neural Networks (CNNs) in image classification tasks has led to increasing interest in interpreting their decisions. Gradient weighted Class Activation Mapping (Grad-CAM) is a post-hoc explanation technique that generates visual heatmaps to highlight the …

    uoit Repository record for Transformation-invariance properties of Grad-CAM in Convolutional Neural Networks (opens in a new tab)

Page 1 of 7