Open Access. Powered by Scholars. Published by Universities.®
Biomedical Engineering and Bioengineering Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Deep learning (3)
- Machine learning (2)
- Active matter (1)
- Adversarial robust (1)
- Adversary attack (1)
-
- Artificial neural network (1)
- Autoencoder (1)
- Classification (1)
- Complex fluids (1)
- Fluid-structure interactions (1)
- Inhomogenous materials (1)
- Joint task learning (1)
- Loss function (1)
- Medical AI (1)
- Microswimmers (1)
- Morphological neural network (1)
- Morphology (1)
- Optimize (1)
- Plaque segmentation (1)
- Scientific computing (1)
- Segmentation (1)
- Siamese network (1)
- Single-cell RNA-seq (1)
- Vessel segmentation (1)
- ZINB (1)
- Publication
Articles 1 - 5 of 5
Full-Text Articles in Biomedical Engineering and Bioengineering
Bacterial Motion And Spread In Porous Environments, Yasser Almoteri
Bacterial Motion And Spread In Porous Environments, Yasser Almoteri
Dissertations
Micro-swimmers are ubiquitous in nature from soil and water to mammalian bodies and even many technological processes. Common known examples are microbes such as bacteria, micro-algae and micro-plankton, cells such as spermatozoa and organisms such as nematodes. These swimmers live and have evolved in multiplex environments and complex flows in the presence of other swimmers and types, inert particles and fibers, interfaces and non-trivial confinements and more. Understanding the locomotion and interactions of these individual micro-swimmers in such impure viscous fluids is crucial to understanding the emergent dynamics of such complex systems, and to further enabling us to control and …
Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue
Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue
Dissertations
The zero-one loss function is less sensitive to outliers than convex surrogate losses such as hinge and cross-entropy. However, as a non-convex function, it has a large number of local minima, andits undifferentiable attribute makes it impossible to use backpropagation, a method widely used in training current state-of-the-art neural networks. When zero-one loss is applied to deep neural networks, the entire training process becomes challenging. On the other hand, a massive non-unique solution probably also brings different decision boundaries when optimizing zero-one loss, making it possible to fight against transferable adversarial examples, which is a common weakness in deep learning …
Towards Adversarial Robustness With 01 Lossmodels, And Novel Convolutional Neural Netsystems For Ultrasound Images, Meiyan Xie
Dissertations
This dissertation investigates adversarial robustness with 01 loss models and a novel convolutional neural net systems for vascular ultrasound images.
In the first part, the dissertation presents stochastic coordinate descent for 01 loss and its sensitivity to adversarial attacks. The study here suggests that 01 loss may be more resilient to adversarial attacks than the hinge loss and further work is required.
In the second part, this dissertation proposes sign activation network with a novel gradient-free stochastic coordinate descent algorithm and its ensembling model. The study here finds that the ensembling model gives a high minimum distortion (as measured by …
Development Of Deep Learning Neural Network For Ecological And Medical Images, Shaobo Liu
Development Of Deep Learning Neural Network For Ecological And Medical Images, Shaobo Liu
Dissertations
Deep learning in computer vision and image processing has attracted attentions from various fields including ecology and medical image. Ecologists are interested in finding an effective model structure to classify different species. Tradition deep learning model use a convolutional neural network, such as LeNet, AlexNet, VGG models, residual neural network, and inception models, are first used on classifying bee wing and butterfly datasets. However, insufficient data sample and unbalanced samples in each class have caused a poor accuracy. To make improvement the test accuracy, data augmentation and transfer learning are applied. Recently developed deep learning framework based on mathematical morphology …
Model-Based Deep Siamese Autoencoder For Clustering Single Cell Rna-Seq Data, Zixia Meng
Model-Based Deep Siamese Autoencoder For Clustering Single Cell Rna-Seq Data, Zixia Meng
Theses
In the biological field, the smallest unit of organisms in most biological systems is the single cell, and the classification of cells is an everlasting problem. A central task for analysis of single-cell RNA-seq data is to identify and characterize novel cell types. Currently, there are several classical methods, such as K-means algorithm, spectral clustering, and Gaussian Mixture Models (GMMs), which are widely used to cluster the cells. Furthermore, typical dimensional reduction methods such as PCA, t-SNE, and ZIDA have been introduced to overcome “the curse of dimensionality”. A more recent method scDeepCluster has demonstrated improved and promising performances in …