MC-CDMA receiver design using recurrent neural networks for eliminating multiple access interference and nonlinear distortion

2017 ◽  
Vol 30 (16) ◽  
pp. e3328 ◽  
Author(s):  
Ravi Kumar C.V. ◽  
Kala Praveen Bagadi
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Multiple Access ◽  
Nonlinear Distortion ◽  
Multiple Access Interference ◽  
Receiver Design ◽  
Cdma Receiver

scholarly journals Spatial Diversity for CDMA RoFSO Links over M Turbulence Channels with Nonzero Boresight Pointing Errors

Computation ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 55
Author(s):  
Michalis Ninos ◽  
Hector Nistazakis
Keyword(s):  
Performance Improvement ◽  
Multiple Access ◽  
Nonlinear Distortion ◽  
Multiple Access Interference ◽  
Spatial Diversity ◽  
Atmospheric Conditions ◽  
Reverse Link ◽  
Pointing Errors ◽  
Link Performance ◽  
Average Bit Error Rate

A CDMA RoFSO link with receivers’ spatial diversity is studied. Turbulence-induced fading, modeled by the M(alaga) distribution, is considered that hamper the FSO link performance along with the nonzero boresight pointing errors effect. Novel, analytical closed-form expressions are extracted for the estimation of the average bit-error-rate and the outage probability of the CDMA RoFSO system for both directions of the forward and the reverse link. The numerical results show clearly the performance improvement of using spatial diversity, even in the most adverse atmospheric conditions with strong and saturated atmospheric turbulence with enhanced misalignment. Also, the effects of nonlinear distortion, multiple access interference and clipping noise aggravate the performance of the link, where cases with large number of users are taken into account.

Spike timing-dependent plasticity in sparse recurrent neural networks

2014 ◽  
Vol 1 ◽  
pp. 485-488
Author(s):  
Hideyuki Kato ◽  
Tohru Ikeguchi
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Spike Timing ◽  
Spike Timing Dependent Plasticity ◽  
Dependent Plasticity

SUPPRESSION OF MULTIPLE ACCESS INTERFERENCE IN UPLINK OFDMA OF MOBILE WiMAX

2015 ◽  
Vol 74 (14) ◽  
pp. 1257-1268
Author(s):  
M. Lakshmanan ◽  
P. S. Mallick ◽  
L. Nithyanandan
Keyword(s):  
Multiple Access ◽  
Multiple Access Interference ◽  
Mobile Wimax

Direct Adaptive Control of Process Systems Using Recurrent Neural Networks

1992 ◽  
Author(s):  
Sanjay Parthasarathy ◽  
Alexander G. Parlos ◽  
Amir F. Atiya
Keyword(s):  
Neural Networks ◽  
Adaptive Control ◽  
Recurrent Neural Networks ◽  
Process Systems ◽  
Direct Adaptive Control

L2 approximation properties of recurrent neural networks

1997 ◽  
Author(s):  
A. Ruiz ◽  
D.H. Owens ◽  
S. Townley
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Approximation Properties

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Sign in / Sign up

Export Citation Format

Share Document