Browsing by Author "Kelly, K.F."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Compressed Domain Image Classification Using a Dynamic-Rate Neural Network(IEEE, 2020) Xu, Y.; Liu, W.; Kelly, K.F.Compressed domain image classification performs classification directly on compressive measurements acquired from the single-pixel camera, bypassing the image reconstruction step. It is of great importance for extending high-speed object detection and classification beyond the visible spectrum in a cost-effective manner especially for resource-limited platforms. Previous neural network methods require training a dedicated neural network for each different measurement rate (MR), which is costly in computation and storage. In this work, we develop an efficient training scheme that provides a neural network with dynamic-rate property, where a single neural network is capable of classifying over any MR within the range of interest with a given sensing matrix. This training scheme uses only a few selected MRs for training and the trained neural network is valid over the full range of MRs of interest. We demonstrate the performance of the dynamic-rate neural network on datasets of MNIST, CIFAR-10, Fashion-MNIST, COIL-100, and show that it generates approximately equal performance at each MR as that of a single-rate neural network valid only for one MR. Robustness to noise of the dynamic-rate model is also demonstrated. The dynamic-rate training scheme can be regarded as a general approach compatible with different types of sensing matrices, various neural network architectures, and is a valuable step towards wider adoption of compressive inference techniques and other compressive sensing related tasks via neural networks.Item Topological metal behavior in GeBi2Te4 single crystals(American Physical Society, 2013) Marcinkova, A.; Wang, J.K.; Slavonic, C.; Nevidomskyy, Andriy H.; Kelly, K.F.; Filinchuk, Y.; Morosan, E.The metallic character of the GeBi2Te4 single crystals is probed using a combination of structural and physical properties measurements, together with density functional theory (DFT) calculations. The structural study shows distorted Ge coordination polyhedra, mainly of the Ge octahedra. This has a major impact on the band structure, resulting in bulk metallic behavior of GeBi2Te4, as indicated by DFT calculations. Such calculations place GeBi2Te4 in a class of a few known nontrivial topological metals, and explains why an observed Dirac point lies below the Fermi energy at about −0.12 eV. A topological picture of GeBi2Te4 is confirmed by the observation of surface state modulations by scanning tunneling microscopy.