{"references": ["R. P. Lippman, \"An introduction to computing with neural nets\", IEEE\nASSP Mag., pp. 4 - 22, Apr. 1987.", "W. W. L. Au, \"Comparison of sonar discrimination - dolphin and\nartificial neural network\", J. Acoust. Soc. Amer., pt. 1, vol. 95, no. 5, pp.\n2728 - 2735, 1994.", "H. L. Roitblat, W. W. L. Au, P. E. Nachtogall, R. Shizumura, and G.\nMoons, \"Sonar recognition of targets embedded in sediment\", Neural\nNetw., vol. 8, no. 7/8, pp. 1263 - 1273, 1995.", "J. A. Simmons, P. A. Saillant, J. M. Wotton, T. Haresign, M. J.\nFeragamo, and C. F. Moss, \"Composition of biosonar images for target\nrecognition by echolocating bats\", Neural Netw., vol. 18, no. 7/8 , pp.\n1239 - 1261, 1995.", "G. B. Willson, \"Radar classification using a neural network\", Proc.\nSPIE, Optical Engineering and Photonics in Aerospace Sensing:\nApplication of Neural Networks, vol. 1294, pp. 200 - 210, 1990.", "S. Watanabe and M. Yoneyama, \"An ultrasonic visual sensor for threedimensional\nobject recognition using neural networks\", IEEE Trans.\nRobot. Automat., vol. 8, pp. 240 - 249, Apr. 1992.", "I. E. Dror, M. Zagaeski, and C. F. Moss, \"3-dimensional target\nrecognition via sonar - a neural network model\", Neural Networks, vol.\n8, no. 1, pp. 149 - 160, 1995.", "R. P. Gorman and T. J. Sejnowski, \"Learned classification of sonar\ntargets using a massively parallel network\", IEEE Trans. Acoust.,\nSpeech, Signal Processing, vol. 36, no. 7, pp. 1135 - 1140, 1998.", "B. Ayrulu and B. Barshan, \"Identification of target primitives with\nmultiple decision-making sonars using evidential reasoning,\" Int. J.\nRobot. Res., vol. 17, no. 6, pp. 598 - 623, 1998.\n[10] L. Yingwei, N. Sundararajan, and P. Saratchandran, \"Performance\nevaluation of a sequential minimal Radial Basis Function (RBF) neural\nnetwork learning algorithm,\" IEEE Trans. Neural Networks, vol. 9, pp.\n308-318, Mar. 1998.\n[11] L. Yingwei, N. Sundararajan, and P. Saratchandran, \"A sequential\nlearning scheme for function approximation using minimal radial basis\nfunction neural networks,\" Neural Computing., vol. 9, pp. 461-478, Feb.\n1997.\n[12] M. Chan, C. Fung, \"Incremental Adaption of Resource-Allocating\nNetwork for Non-Stationary Time Series,\" Neural Networks, 1999.\nIJCNN '99. IEEE International Joint Conference, Volume: 3 , 10-16,\nJuly 1999, pp. 1554 -1559 vol.3\n[13] B. L. Pulito, T. R. Damarla, S. Nariani, \"A Two-Dimensional Shift\nInvariant Image Classification Neural Network which overcomes the\nStability / Plasticity Dilemma,\" Neural Networks, 1990., 1990 IJCNN\nInternational Joint Conference on 17-21 June 1990, pp. 825 -833, vol.2\n[14] J. P. Albright, \"An implementation and Evaluation of the ART1 Neural\nNetwork For Pattern Recognition,\" Neural Networks, 1994. IEEE World\nCongress on Computational Intelligence., 1994 IEEE International\nConference, Volume: 1 , 27 June-2 July 1994, pp. 498 -502, vol.1\n[15] Youngtae Park, \"An ART2 trained Two-Stage Learning on Circularly\nOrdered Data Sequence,\" Neural Networks, 1994. IEEE World Congress\non Computational Intelligence., 1994 IEEE International Conference,\nVolume: 5 , 27 June-2 July 1994, pp. 2928 -2933, vol.5\n[16] Rok Rape, Dusan Fefer, Janko Drnovsek. Time Series Prediction with\nNeural Networks: A Case Study of Two Examples, IMTC-94, IEEE,\nMay 1994.\n[17] Ben Jacobsen. Time Series Properties of Stock Returns, Kluwer\nBedrijfsInformatie, 1997.\n[18] Donald F. Specht, \"Enhancements To Probabilistic Neural Networks,\"\nNeural Networks, 1992. IJCNN., IEEE International Joint Conference,\nVolume: 1 , 7-11, June 1992, pp. 761 - 768, vol.1\n[19] B. Barshan, B. Ayrulu, and S. W. Utete, \"Neural Network-Based Target\nDifferentiation Using Sonar for Robotics Applications,\" IEEE Trans.\nRobotics and Automation, vol. 16, pp. 435 - 442, August 2000.\n[20] N. Sundararajan, P. Saratchandran and, Lu Ying Wei, book of \"Radial\nBasis Function Neural Network,\" by School of Electrical & Electronic\nEngineering, Nanyang Tech. Univ, S-pore.\n[21] W. S. Lim, M.V.C. Rao, C.K. Loo,\"Sequential Learning Neural\nNetwork For Sonar Target Differentiation,\" Neural Network World 2/04,\n187-197.\n[22] D. F. Specht, \"Probablistic Neural Networks,\" Neural Networks 3 (1990)\n109-118.\n[23] D. F. Specht, \"Probabilistic neural networks for classification, mapping,\nor associative memory,\" ICNN, vol.1 (San Diego, CA), July 1988, pp.\n525-532.\n[24] D. J. Marchette and C. E. Priebe, \"The adaptive kernel neural network,\"\nReports: AD-A217 230, 1989.\n[25] P. S. Naloney, \"The use of probabilistic neural networks to improve\nsolution times for hull-to-emitter correlation problems,\" IJCNN,\nSheraton Washington, Vol.1, 1989, pp. 289-294.\n[26] D. F. Specht, \"Application of probabilistic neural networks,\" SPIE,\nAppl. Artif. Neural Networks 1294 (1990) 344-353.\n[27] J. J. Guo, P. B. Luh, \"Selecting input factors for clusters of Gaussian\nradial basis function networks to improve market clearing price\nprediction,\" Power Systems, IEEE Transactions, Volume 18, Issue 2,\nMay 2003 Page(s):665 - 672.\n[28] G. B. Huang, P. Saratchandran, N. Sundararajan, \"A generalized\ngrowing and pruning RBF neural network for function approximation,\"\nNeural Networks, IEEE Transactions, Volume 16, Issue 1, Jan. 2005\nPage(s):57 - 67.\n[29] G. B. Huang, P. Saratchandran, N. Sundararajan, \"An efficient\nsequential learning algorithm for growing and pruning RBF networks,\"\nSystems, Man and Cybernetics, Part B, IEEE Transactions, Volume 34,\nIssue 6, Dec. 2004 Page(s):2284 - 2292."]}

In this paper, the processing of sonar signals has been carried out using Minimal Resource Allocation Network (MRAN) and a Probabilistic Neural Network (PNN) in differentiation of commonly encountered features in indoor environments. The stability-plasticity behaviors of both networks have been investigated. The experimental result shows that MRAN possesses lower network complexity but experiences higher plasticity than PNN. An enhanced version called parallel MRAN (pMRAN) is proposed to solve this problem and is proven to be stable in prediction and also outperformed the original MRAN.