… It allows learning of transmitter and receiver implementations as deep neural networks (NNs…
-defined radios and open-source deep learning software libraries. We extend the existing …

… , we propose a “one-to-many” deep learning technique that can analyze non-sinusoidal fringe
… We show for the first time, to the best of our knowledge, a trained deep neural network can …

… as AMP, lattice decoding, sphere decoding, conditional maximum-likelihood decoding,
etc., … For instance, the sphere decoder is a search algorithm that performs maximum-likelihood …

… saliency features in both spatial and temporal domains and an Spherical CNN incorporated
deep learning approach to obtain spherical features only in the spatial domain. Secondly, …

… Hence, in this work, we propose a low switching fixed-complexity sphere decoder (LSFSD)
that can use the same tree structure as FSD/IFSD. However, we preferred the IFSD tree …

… However, the irregular structure complicates the usage of point clouds in deep learning.
Qi et al. [31] proposed PointNet for point cloud classification and segmentation. …

… new results in the field of deep learning in Chapter 9. We … simulation results where deep
learning is used to decode/detect. … 6See Chapter 4 for more information on the sphere decoder. …

… Recently, deep learning has been used to predict the distance from … Deep learning improves
optical microscopy, enhancing its … through diffractive pattern learning using deep learning. …

… edge details better than existing deep learning models. … In this study, we investigated a deep
learning-based SISR process … The clinical validation of the deep learning model will provide …

… The application of deep learning (DL) models to … (1) decodes the cognitive states underlying
the fMRI data more accurately than these other approaches, (2) improves its decoding …