Some new neural network architectures with improved learning schemes

Soft Computing

Volumn 4, Issue 4, 2000, Pages 214-223

  Sinha, M ^a   Kumar, K ^a   Kalra, P K ^a  

^a INDIAN INSTITUTE OF TECHNOLOGY KANPUR   (India)

Author keywords

Compensatory architecture; Complex backpropagation; Higher order neurons; Lambda gamma learning algorithm; Self scaling scaled conjugate gradient algorithm; Sigma pi sigma architecture

Indexed keywords

ALGORITHMS; BACKPROPAGATION; BACKPROPAGATION ALGORITHMS; BUDGET CONTROL; COMPLEX NETWORKS; CONJUGATE GRADIENT METHOD; ITERATIVE METHODS; LEARNING ALGORITHMS; NEURAL NETWORKS; NEURONS; ORBITS;

AGGREGATION FUNCTIONS; COMPUTATIONAL BUDGET; FASTER CONVERGENCE; FEED-FORWARD ARCHITECTURES; HIGHER-ORDER; PREDICTION ACCURACY; SATELLITE ORBIT DETERMINATION; SCALED CONJUGATE GRADIENT ALGORITHM;

NETWORK ARCHITECTURE;

EID: 3142593934     PISSN: 14327643     EISSN: 14337479     Source Type: Journal    
DOI: 10.1007/s005000000057     Document Type: Article

References (35)

1. Albus JS (1975a) Data storage in cerebellar model architecture controller (CMAC). Trans of ASME, J Dynamic Systems, Measurement and Control 97: 225-233
2. Albus JS (1975b) A new approach to manipulator control: the cerebellar model controller (CMAC). Trans ASME, J Dynamic Systems, Measurement and control 97: 220-227
3. Battiti R (1992) First and second-order methods for learning: between steepest descent and Newton's method, Neural Computation 2: 141-166
4. Battiti R, Masulli F (1990) BFGS optimization for faster automated supervised learning. In: Int. Neural Network Conf., vol. 2, pp. 757-760
5. Dzielinsky AS, Skoneczny R, Kuklinsky S (1990) Cellular neural network application to moire pattern filtering. In: Proc. IEEE CNNA workshop, Budapest, Hungry
6. Elman JL (1990) Finding structure in time. Cognitive Science 14: 179-211
7. Engelbrecht AP, Cloete I, Geldenhuys J, Zurada JM (1995) Automatic scaling using gamma learning for feedforward neural networks, From Natural to Artificial Computing. Lecture Notes in Computer science 930: 373-381
8. Fahlman SE (1988) Fast learning variations on backpropagation: an empirical study. In: Touretzky DS, Hinton G, Sejnowski T (eds.) Proc. Connectionist Models Summer School, Pittsburg, eds., pp. 38-51 Morgan Kaufmann, San Mateo, CA 1989
9. Grossberg S (1988) Neural networks and natural intelligence. The MIT Press, Cambridge, MA
10. Hecht-Nielsen R (1987b) Kolmogorov's mapping neural network existence theorem. In: Proc IJCNN, (San Diego, 1987), vol. III, pp. 11-14, IEEE New York
11. Huang SJ, Huang SL (1996) Static security assessment of a large-scale power system using genetic-enhanced neural network approaches. In: Proc. Nat. Sci. Council, China, Part A: Physical Sci Eng 20(2): 228-235
12. Ichimura T, Takano T, Tazaki E (1996) Learning of neural networks using hybrid genetic algorithm. In: 4th European Congr. Intell. Techniques and Soft Computing (EUFIT'96)
13. Jacobs A (1988) Increased rate of learning convergence through learning adaptation. Neural networks 1: 295-307
14. Johansson EM. Dowla FU, Goodman DM (1991) Backpropagation learning for multi-layer feedforward neural networks using the conjugate gradient method. Int. J. Neural Systems 2(4): 291-302
15. Jordan M (1989) Generic constraints on unspecified target trajectories. In: Proc IEEE Int Joint Conf. neural networks
16. Kawato M (1990) Computational schemes and neural network models for formation and control of multijoint arm trajectory. In: Miller WT, Sutton R, Werbos P (eds.) Neural networks for Robotics and Control, Cambridge, MIT Press, MA
17. Lane SH, Handelman DA, Gelfand JJ (1991) Higher order CMAC neural networks - theory and practice. In: Proc. American Control Conf., pp. 1529-1585 Boston, MA
18. Lightbody G (1993) Identification and control using neural networks. Ph.D. dissertation, Advanced Control Engineering research group, Queen's Univ. Belfast UK
19. Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural networks 6: 525-533
20. Narendra R (1990) Adaptive control using neural networks. In: Miller WT, Sutton R, Werbos P (eds.) Neural Networks for Robotics and Control, Cambridge, MIT Press, MA
21. Nelles O, Sinsel S, Isermann R (1996) Local basis function networks for identification of a turbocharger. In: Proc UKACC Int Conf Cont' 96, pp. 7-12. Exeter, UK
22. Nguyen D, Widrow B (1990) The truck backer-upper: an example of self learning in neural networks. In: Miller WT, Sutton R, Werbros P (eds.) Neural Networks for Robotics and control, Cambridge, MIT Press, MA
23. Nitta T (1997) An extension of the Backpropagation Algorithm to Complex Numbers. Neural Networks 10(4): 1391-1415
24. Sato A, Yamada K, Tsoknmo J, Temma T (1991) Artificial Neural Networks. In: Kohonnen T, Mahasara K, Simula O, Kangas J (eds.) Elsevier Science Publication, B.V. (North- Holland)
25. Sawai H, Waibel A, Haffnes P, Miyatake M, Shikano K (1989) Parallelism, hierarchy, scaling in time-delay neural networks for spotting Japanese phonemes/CV-syllables. In: Proc. IEEE Int Joint Conf. neural Networks
26. Schiffmann W, Joost M, Werner R (1992) Optimization of the backpropagation algorithm for multilayer perceptrons, Univ. Koblenz, Inst. Physics, Rheinau 3-4, W-5400 Koblenz, Germany
27. Shamma SA (1989a) Spatial and temporal processing in central auditory networks. In: Koch C, Egev L (eds.) Methods in Neural Modeling, pp. 247-289, MIT Press, Cambridge MA
28. Sinha M, Kumar K, Kalra PK Neural network alternative to Kalman filter for satellite orbit determination (communicated to IEEE Aerospace and Electronic Systems)
29. Van Der Smagt P (1994) Minimization methods for training feedforward neural networks. Neural Networks 7(1): 1-11
30. Wasserman PD (1989) Neural computing, theory and practice van Nostrand Reinhold, New York
31. Watrous R, Shastri L (1987) Learning phonetic features using connectionist networks: an experiment in speech recognition. In: Proc. 1st IEEE Int. Conf. Neural Networks
32. Watta PB, Hassoun MH, Meisel J (1996) Design of optimal neurocontrollers for the separately excited dc motor using a hybrid genetic algorithm-neural network approach. In: Proc SPIE-Int Soc Opt Eng 2760: 230-240
33. Werbos P (1994) Beyond Regression: new tools for prediction and analysis in behavioral science, Ph.D. dessertation, Committee on Applied Mathematics, Harvard Univ., Cambridge, MA
34. Willis MJ, Di Massimo C, Montague GA (1991) Tham, Artificial neural networks in process engineering. In: Proc Inst Elect Eng Control Theory and application 128(3): 256-164
35. Zurada JM (1992) Lambda learning rule for feedforward neural networks, Proc. of IEEE Int. Conf. on Neural Networks, San Francisco, California