Automated design of deep neural networks: A survey and unified taxonomy

EG Talbi - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
In recent years, research in applying optimization approaches in the automatic design of
deep neural networks has become increasingly popular. Although various approaches have …

Concealnet: An end-to-end neural network for packet loss concealment in deep speech emotion recognition

MM Mohamed, BW Schuller - arXiv preprint arXiv:2005.07777, 2020 - arxiv.org
Packet loss is a common problem in data transmission, including speech data transmission.
This may affect a wide range of applications that stream audio data, like streaming …

Optimization of deep neural networks: a survey and unified taxonomy

EG Talbi - 2020 - inria.hal.science
During the last years, research in applying optimization approaches in the automatic design
of deep neural networks (DNNs) becomes increasingly popular. Although various …

Real-time lossy audio signal reconstruction using novel sliding based multi-instance linear regression/random forest and enhanced cgpann

NM Khan, GM Khan - Neural Processing Letters, 2021 - Springer
This paper proposes a novel NeuroEvolutionary algorithm called Enhanced Cartesian
Genetic Programming evolved Artificial Neural Network (ECGPANN) as a predictor for the …

Multi-chromosomal CGP-evolved RNN for signal reconstruction

NM Khan, GM Khan - Neural Computing and Applications, 2021 - Springer
A multi-chromosomal structure for neuro-evolution of recurrent neural networks (RNNs) with
Cartesian genetic programming (CGP) architecture is presented to develop a signal …

Signal Reconstruction Using Computational Intelligence Techniques

NM Khan - 2021 - search.proquest.com
This thesis develops and implements computational intelligence techniques for restor-ing
lost signal samples through estimation and a complete signal recovery through multivariable …