OFDM Multiple Antennas Cognitive Radio Relay Synchronization CDMA Channel Estimation Spectrum Sharing Interference Cancellation Full duplex Spectrum Sensing Neural Networks Resource Allocation Stochastic Geometry Equalizer Bi-Directional Feedback Femtocell Heterogeneous Networks Energy Harvesting Device-to-Device (D2D) Cell Search Spectral efficiency NOMA FBMC interference management Dynamic TDD Cross-link interference SINR mismatch problem HetNet Idle cells Ultra-dense small cell networks achievable sum rate outage probability multi-spectral full-duplex relay selection diversity bursty traffic model mode selection Handoff CP-OFDM non-orthogonal multiple access self-interference cancellation Singular Vale Decomposition interference mitigation full-duplex cellular interference coordination Cognitive relay networks Time spreading beamforming Link adaptation Heterogeneous channel estimation capability coexistence MU-MIMO full-spreading NOMA GFDM Bi-directional full-duplex OQAM sensing duration Correlated MIMO Simultaneous Sensing and Transmission transmission capacity (TC) Two-way communications in-band full-duplex system automatic repeat request (ARQ) UWB flexible duplex TS-W-OFDM Windowing time-frequency efficiency eigen decomposition pilot signal 5G networks prototype filter Aggregate interference Long Term Evolution-Advanced interference to noise ratio resource size control link reliability mixed numerology Vehicle-to-vehicle communication LTE-based V2V Coexistence scenarios Resource management Filtered OFDM Cooperative systems Complexity tabu-search Deep learning Reliability Vehicle-to-Vehicle C-V2V HST Mobility Preamble 5G Grant-free Transmission Asynchronous Transmission Railway MLP massive connectivity
Status : Published 
Date : 1990-06 
Title : Parallel, Self-Organizing Hierarchical Neural Networks 
Authors : Daesik Hong and Okan K. Ersoy 
Journal : IEEE Transactions on Neural Networks 
Abstract : A new neural-network architecture called the parallel, self-organizing, hierarchical neural network (PSHNN) is presented. The new architecture involves a number of stages in which each stage can be a particular neural network (SNN). At the end of each stage, error detection is carried out, and a number of input vectors are rejected. Between two stages there is a nonlinear transformation of input vectors rejected by the previous stage. The new architecture has many desirable properties, such as optimized system complexity (in the sense of minimized self-organizing number of stages), high classification accuracy, minimized learning and recall times, and truly parallel architectures in which all stages operate simultaneously without waiting for data from other stages during testing. The experiments performed indicated the superiority of the new architecture over multilayered networks with back-propagation training 
URL : http://ieeexplore.ieee.org/xpl/articleDe...mber=80229 

Ersoy, O.K.; Hong, D.; , "Parallel, self-organizing, hierarchical neural networks," Neural Networks, IEEE Transactions on , vol.1, no.2, pp.167-178, Jun 1990
doi: 10.1109/72.80229
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=80229&isnumber=2633

List of Articles
Status Datesort
3 [IEEE Trans. Neural Netw.] KyunByoung Ko, Sooyong Choi, Changeon Kang and Daesik Hong, "RBF Multiuser Detector With Channel Estimation Capability in a Synchronous MC-CDMA System", IEEE Trans. Neural Networks, Nov 2001 Published  2001-11 
2 [IEEE Trans. Neural Netw.] Cheolwoo You and Daesik Hong, "Nonlinear Blind Equalization Schemes Using Complex-valued Multilayer Feedforward Neural Networks", IEEE Trans. Neural Networks, Nov 1998 Published  1998-11 
» [IEEE Trans. Neural Netw.] Daesik Hong and Okan K. Ersoy, "Parallel, Self-Organizing Hierarchical Neural Networks", IEEE Trans. Neural Net., June 1990 Published  1990-06