Search
Now showing items 1-10 of 16
Loss Landscapes and Generalization in Neural Networks: Theory and Applications
(Johns Hopkins University, 2020-01-21)
In the last decade or so, deep learning has revolutionized entire domains of machine learning. Neural networks have helped achieve significant improvements in computer vision, machine translation, speech recognition, etc. ...
Malicious Network Traffic Detection via Deep Learning: An Information Theoretic View
(Johns Hopkins University, 2020-08-18)
The attention that deep learning has garnered from the academic community and industry continues to grow year over year, and it has been said that we are in a new golden age of artificial intelligence research. However, ...
DEEP LEARNING FRAMEWORK FOR CHARACTER RECOGNITION IN LOW QUALITY LICENSE PLATE IMAGES
(Johns Hopkins University, 2020-10-27)
Commercially available Automatic License Plate Recognition (ALPR) systems have limited
ability to provide character recognition on low-quality license plate images [20]. Improving this
ability would be beneficial for tasks ...
Development of a Protein Folding Environment for Reinforcement Learning
(Johns Hopkins University, 2020-08-12)
The prediction of the three-dimensional protein structures from amino acid sequences has been a long-standing challenge in computational biophysics. In the last decade, considerable progress has been made by leveraging ...
DEEP LEARNING FOR VOLUMETRIC MEDICAL IMAGE SEGMENTATION
(Johns Hopkins University, 2020-12-27)
Over the past few decades, medical imaging techniques, e.g., computed tomography (CT), positron emission tomography (PET), have been widely used to improve the state of diagnosis, prognosis, and treatment of diseases. ...
3D Attention M-net for Short-axis Left Ventricular Myocardium Segmentation in Mice MR cardiac Images
(Johns Hopkins University, 2021-05-11)
Small rodent cardiac magnetic resonance imaging (MRI) plays an important role in preclinical models of cardiac disease, which is routinely used to probe the effect of individual genes or groups of genes on the etiology of ...
NEW ROLES FOR EXTRACELLULAR VESICLES AND DIGITAL PATHOLOGY IN STIFFNESS-MEDIATED CANCER PROGRESSION
(Johns Hopkins University, 2021-03-16)
An increase in extracellular matrix stiffness enhances cancer cell migration and proliferation at the primary tumor. While essential to our understanding of solid tumor progression, the study of cell and tissue mechanics ...
On the Data Efficiency and Model Complexity of Visual Learning
(Johns Hopkins University, 2021-07-01)
Computer vision is a research field that aims to automate the procedure of gaining abstract understanding from digital images or videos. The recent rapid developments of deep neural networks have demonstrated human-level ...
Ultrasound Imaging with Flexible Array Transducer
(Johns Hopkins University, 2021-05-10)
Ultrasound imaging has been developed for image-guided radiotherapy for tumor tracking, and the flexible array transducer is a promising tool for this task. It can reduce the user dependence and anatomical changes caused ...
STATISTICAL AND MACHINE LEARNING APPROACHES FOR SEMANTIC SEGMENTATION AND SURVIVAL ANALYSIS
(Johns Hopkins University, 2021-06-25)
Machine learning and, in particular, deep learning have been sweeping many disciplines in recent years. Advancements in neural networks, the primary tool of deep learning, have made them the go-to approach in a variety of ...