Abstract
Two sets of studies examined the viability of using bat-like sonar input for artificial neural networks in complex pattern recognition tasks. In the first set of studies, a sonar neural network was required to perform two face recognition tasks. In the first task, the network was trained to recognize different faces regardless of facial expressions. Following training, the network was tested on its ability to generalize and correctly recognize faces using echoes of novel facial expressions that were not included in the training set. The neural network was able to recognize novel echoes of faces almost perfectly (above 96% accuracy) when it was required to recognize up to five faces. In the second face recognition task, a sonar neural network was trained to recognize the sex of 16 faces (eight males and eight females). After training, the network was able to correctly recognize novel echoes of those faces as ‘male’ or as ‘female’ faces with accuracy levels of 88%. However, the network was not able to recognize novel faces as ‘male’ or ‘female’ faces. In the second set of studies, a sonar neural network was required to learn to recognize the speed of a target that was moving towards the viewer. During training, the target was presented in a variety of orientations, and the network's performance was evaluated when the target was presented in novel orientations that were not included in the training set. The different orientations dramatically affected the amplitude and the frequency composition of the echoes. The neural network was able to learn and recognize the speed of a moving target, and to generalize to new orientations of the target. However, the network was not able to generalize to new speeds that were not included in the training set. The potential and limitations of using bat-like sonar as input for artifical neural networks are discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ahalt SC, Garber FD, Jouny I, Krishnamurthy AK (1989) Performance of synthetic neural network classification of noisy radar signals. In: Lippman RP, Moody JE, Touretzky DS (eds) Advances in neural information processing systems 1. Morgan Kaufmann, San Mateo, Calif
Au WWL (1993) The sonar of dolphins. Springer, Berlin Heidelberg New York
Bengio Y, Cardin R, De Mori R, Cosi P (1989) Use of multi-layered networks for coding speech with phonetic features. In: Lippman RP, Moody JE, Touretzky DS (eds) Advances in neural information processing systems 3. Morgan Kaufmann, San Mateo, Calif
Busnel R-G, Fish JF (1980) Animal sonar systems. Plenum Press, New York
Cottrell GW, Metcalfe J (1991) Empath: face, emotion, and gender recognition using holons. In: Lippman RP, Moody JE, Touretzky DS (eds) Advances in neural information processing systems 3. Morgan Kaufmann, San Mateo, Calif
De Renzi E (1986) Current issues in prosopagnosia. In: Ellis HD, Jeeves MA, Newcome F, Young A (eds) Aspects of face processing. Martinus Nijhoff, Dordrecht
Dror IE (1994) Neural network models as tools for understanding high-level cognition: Developing paradigms for cognitive interpretation of neural network models. In: Mozer MC, Smolensky P, Touretzky DS, Elman JL, Weigend AS (eds) Proceedings of the 1993 Connectionist Models Summer School. Erlbaum, Hillsdale, NJ, pp 87–94
Dror IE, Dascal M (1996) Can Wittgenstein help free the mind from rules? The philosophical foundations of connectionism. In: Johnson D, Erneling C (eds) Reassessing the cognitive revolution: Alternative futures. Oxford University Press, Oxford (in press)
Dror IE, Young MJ (1994) The role of neural networks in cognitive science: Evolution or revolution? Psycholoquy 5:79
Dror IE, Zagaeski M, Moss CF (1995) Three-dimensional target recognition via sonar: A neural network model. Neural Networks 8:149–160
Dror IE, Zagaeski M, Rios D, Moss CF (1996) Sonar as a perceptual modality for robotics. In: Smagt P (ed) Neural systems and robotics. Ablex Press, Norwood, NJ (in press)
Emde Gvd, Menne D (1989) Discrimination of insect wingbeat-frequency by the bat Rhinolophus ferrumenquinum. J Comp Physiol A 164:663–671
Gjerdingen RO (1992) Learning syntactically significant temporal patterns of chords: A masking field embedded in an ART 3 architecture. Neural Networks 5:551–564
Goldstein AG, Chance JE (1970) Visual recognition memory for complex configurations. Percept Psychophys 9:237–241
Golomb BA, Lawrence DT, Sejnowski TJ (1991) Sexnet: a neural network identifies sex from human faces. In: Lippman RP, Moody JE, Touretzky DS (eds) Advances in neural information processing systems 3. Morgan Kaufmann, San Mateo, Calif
Gorman RP, Sejnowski TJ (1988) Analysis of hidden units in a layered network trained to classify sonar targets. Neural Networks 1: 75–89
Griffin DR (1958) Listening in the dark. Yale University Press, New Haven, Conn
Haken H, Kelso JAS, Fuchs A, Pandya AS (1990) Dynamic Pattern recognition of coordinated biological motion. Neural Networks 3:395–401
McQuoid MRJ (1993) Neural ensembles: simultaneous recognition of multiple 2-D visual objects. Neural Networks 6:907–917
Moore PWB, Roitblat HL, Penner RH, Nachtigall PE (1991) Recognizing successive dolphin echoes with an integrator gateway network. J Neural Networks 4:701–709
Nachtigall PE, Moore PWB (1988) Animal sonar: Processes and performance. Plenum Press, New York
Pomerleau DA (1991) Rapidly adapting artificial neural networks for autonomous navigation. In: Lippman RP, Moody JE, Touretzky DS (eds) Advances in neural information processing systems 3. Morgan Kaufmann, San Mateo, Calif.
Roitblat HL, Moore PWB, Nachtigall PE, Penner RH, Au WWL (1989) Natural echolocation with an artificial neural network. Int J Neural Networks 4:239–248
Rumelhart DE, Hinton GE, Williams RJ (1988) Learning internal representations by error propagation: In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing: Exploration in the microstructure of cognition, vol 1, Foundations. MIT Press, Cambridge, Mass.
Schnitzler H-U, Menne D, Kober R, Heblich K (1983) The acoustical image of fluttering insects in echolocation bats. In: Huber F, Markel H (eds) Neuroethology and behavioral physiology. Springer, Berlin Heidelberg New York, pp 235–249
Schreiber A, Rousset S, Tiberghien G (1991) Facenet: a connectionist model of face identification in context. Eur J Cogn Psychol 3: 177–198
Silverman RH, Noetzel AS (1990) Image processing and pattern recognition in ultrasonagrams by backpropagation. Neural Networks 3:593–603
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cogn Neurosci 3:71–86
Yao Y, Freeman WJ, Burke B, Yang O (1991) Pattern recognition by a distributed neural network: An industrial application. Neural Networks 4:103–121
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dror, I.E., Florer, F.L., Rios, D. et al. Using artificial bat sonar neural networks for complex pattern recognition: Recognizing faces and the speed of a moving target. Biol. Cybern. 74, 331–338 (1996). https://doi.org/10.1007/BF00194925
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF00194925