Zobrazeno 1 - 4
of 4
pro vyhledávání: '"KRZYSTON, JAKOB"'
Autor:
Balwani, Aishwarya, Krzyston, Jakob
Modern-day neural networks are famously large, yet also highly redundant and compressible; there exist numerous pruning strategies in the deep learning literature that yield over 90% sparser sub-networks of fully-trained, dense architectures while st
Externí odkaz:
http://arxiv.org/abs/2206.06563
I/Q modulation classification is a unique pattern recognition problem as the data for each class varies in quality, quantified by signal to noise ratio (SNR), and has structure in the complex-plane. Previous work shows treating these samples as compl
Externí odkaz:
http://arxiv.org/abs/2010.10717
Transceivers used for telecommunications transmit and receive specific modulation patterns that are represented as sequences of complex numbers. Classifying modulation patterns is challenging because noise and channel impairments affect the signals i
Externí odkaz:
http://arxiv.org/abs/2010.15556
Publikováno v:
Fine Focus. 2016, Vol. 2 Issue 2, p104-115. 12p.
