OFDM Relay Cognitive Radio Multiple Antennas Resource Allocation Full Duplex Spectrum Sensing Synchronization Spectrum Sharing Interference Cancellation Channel Estimation Feedback Stochastic Geometry Heterogeneous Networks Bi-directional Energy Harvesting relay networks FBMC Equalization interference Duplex CDMA SC-FDMA HetNet interference suppression Ultra Low Power TVWS 5G channel capacity in-band full-duplex system QAM intersymbol interference intercarrier interference quality of service amplify and forward communication Zigbee cellular radio telecommunication traffic 5G mobile communication LTE-TDD distributed mode power uncertainty SCMA frame structure health care antenna arrays body area networks timing misalignment MIMO User association Outdated channel estimation self interference cancellation C-V2V ultra-dense small cell network channel estimation error Full-duplex Timing and frequency offset resource block management UFMC Handoff System level simulation Empty cell Ultra-dense small cell On/off algorithm CoMP Metaheuristics Power control MPA detector End-to-end delay mMTC Short burst transmission Traffic Poisson arrival Capacity Time-division duplex Subband filtering OCBT Waveforms Vehicle-to-vehicle communication Spatial capacity LTE-based V2V Communication range CFO Reliability Uplink SCMA system resource selection maximum likelihood method Vehicular communication V2X P-NOMA partial overlap QR Factorization FS-NOMA Dynamic TDD Number of training blocks cross-link interference user fairness Multi-user Receiver Mode 3 non-orthogonal multiple access
Status : Presented 
Date : 2001-07 
Title : A Multilayer Feedforward Neural Network Having N/4 nodes in Two Hidden Layers 
Authors : Sooyong Choi, KyunByoung Ko and Daesik Hong 
Conference : IEEE International Joint Conference on Neural Networks 
Abstract : In order to reduce the complexity of a single hidden layer multilayer neural network, a new two hidden layer MFNN (THL-MFNN) with a combined structure of a RBFN and MLPs is proposed, and its associated training method is discussed. The proposed THL-MFNN can be easily constructed, and can be efficiently trained by online recursive methods. The performance of the proposed THL-MFNN with P/4+2=18 hidden nodes and 34 weights is equal to that of an optimum Bayesian equalizer using an RBFN with P=64 hidden nodes and 64 weights. The role of each layer in the proposed THL-MFNN is presented by a theoretical approach, and the feasibility of a more reduced structure is given 
URL : http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=938413 
Download : http://mirinae.yonsei.ac.kr/?module=file...94d708d23e 

 Sooyong Choi; Kyunbyoung Ko; Daesik Hong; , "A multilayer feedforward neural network having N/4 nodes in two hidden layers," Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on , vol.3, no., pp.1675-1680 vol.3, 2001
doi: 10.1109/IJCNN.2001.938413
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=938413&isnumber=20319

List of Articles
No.
Status Datesort
9 [IEEE IJCNN] Sooyong Choi, KyunByoung Ko and Daesik Hong, "Equalization Techniques Using A Simplified Bilinear Recursive Polynomial Perceptron with Decision Feedback", IJCNN, Jun. 2001 Presented  2001-07 
» [IEEE IJCNN] Sooyong Choi, KyunByoung Ko and Daesik Hong, "A Multilayer Feedforward Neural Network Having N/4 nodes in Two Hidden Layers", IJCNN, Jun. 2001 file Presented  2001-07 
7 [IEEE IJCNN] KyunByoung Ko, Sooyong Choi, Changeon Kang and Daesik Hong, "A Simplified multiuser Receiver of DS-CDMA System", IJCNN, Jul. 2001 file Presented  2001-07 
6 [IEEE IJCNN] Kyunbyoung Ko, Sooyong Choi and Daesik Hong, "Multi-User Detector with an ability of channel estimation using a RBF network in an MC-CDMA System", IEEE IJCNN, July 2000 Presented  2000-07 
5 [IEEE IJCNN] Sooyong Choi and Daesik Hong, "Equalization Using the Bilinear Recursive Polynomial Perceptron with Decision Feedback", IEEE IJCNN, July 2000 Presented  2000-07 
4 [IEEE IJCNN] Sooyong Choi and Daesik Hong, "A Hybrid Structured Neural Network Receiver in Digital Communication Systems", IEEE IJCNN, July 2000 Presented  2000-07 
3 [IEEE IJCNN] Sooyong Choi and Daesik Hong, "'Performance of RBF equalizer in data storage channels", IEEE IJCNN, Jul. 1999 Presented  1999-07 
2 [IEEE IJCNN] Kyunggoo Lee, Cheolwoo You, Sooyong Choi, Sunghwan Ong and Daesik Hong, "Performance Evaluation of Neural Equalizers for the DVD-ROM System", IEEE IJCNN, May, 1998 Presented  1998-05 
1 [IEEE IJCNN] Daesik Hong and O. K. Ersoy, "A Hierarchical Neural Networks Involving Nonlinear Spectral Processing",IEEE IJCNN., June 1989 Presented  1989-06