Skip to main content
SpringerLink
Log in

Artificial neural network classification of Drosophila courtship song mutants

  • Published:
Biological Cybernetics Aims and scope Submit manuscript

Abstract

Courtship songs produced by Drosophila males — wild-type, plus the cacophony and dissonance behavioral mutants — were examined with the aid of newly developed strategies for adaptive acoustic analysis and classification. This system used several techniques involving artificial neural networks (a.k.a. parallel distributed processing), including learned vector quantization of signals and non-linear adaption (back-propagation) of data analysis. “Pulse” song from several individual wild-type and mutant males were first vector-quantized according to their frequency spectra. The accumulated quantized data of this kind, for a given song, were then used to “teach” or adapt a multiple-layered feedforward artificial neural network, which classified that song according to its original genotype. Results are presented on the performance of the final adapted system when faced with novel test data and on acoustic features the system decides upon for predicting the song-mutant genotype in question. The potential applications and extensions of this new system are discussed, including how it could be used to screen for courtship mutants, search novel behavior patterns or cause-and-effect relationships associated with reproduction, compress these kinds of data for digital storage, and analyze Drosophila behavior beyond the case of courtship song.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Ahalt S, Hipman TR (1989) An improved self-organization feature map. Int Joint Conf Neural Network I:241–246

    Google Scholar 

  • Atal BS (1982) Predictive coding of speech at low bit rates. IEEE Trans Commun COM-30:600–614

    Google Scholar 

  • Bernstein, AS, Neumann EK, Hall JC (1992) Temporal analysis of tone pulses within the courtship songs of two sibling Drosophila species, their interspecific hybrid, and behavioral mutants of D. melanogaster. J Insect Behav, 5:15–36

    Google Scholar 

  • Bounds DG, Lloyd PJ, Mathew G (1990) A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders. Neural Networks 3:583–591

    Google Scholar 

  • Brunak S, Engelbrecht J, Knudsen S. (1990) Detection of errors in mRNA splice site assignments by neural network. Nature 343:123

    Google Scholar 

  • Chatfield C, Lemon, RE (1970) Analyzing sequences of behavioral events. J Theor Biol 29:427–445

    Google Scholar 

  • Cook R (1979) The courtship tracking of Drosophila melanogaster. Biol Cybern 34:91–106

    Google Scholar 

  • Cook R (1980) The extent of visual control in the courtship tracking of D. melanogaster. Biol Cybern 37:41–53

    Google Scholar 

  • Cover TM, Hart PE (1967) Nearest neighbor pattern classification. IEEE Trans Inform Theory IT 13:21–27

    Google Scholar 

  • Cowling DE, Burnet B (1981) Courtship song and genetic control of their acoustic characteristics in sibling species of the Drosophila melanogaster subgroup. Anim Behav 29:924–935

    Google Scholar 

  • Dietz WE, Kiech EL, Ali M (1989) Jet and rocket engine fault diagnosis in real time. J Neural Network Comput 1:5–18

    Google Scholar 

  • Dowse HB, Ringo JM (1989) The search for hidden periodicities in biological time series revisited. J Theor Biol 139:487–515

    Google Scholar 

  • Elman JL (1988) Finding structure in time. Technical Report 8801. Center of Research in Language, La Jolla CA, USA

    Google Scholar 

  • Ewing AW (1977) Communication in Diptera. In: Sebeok T (eds) How animals communicate, Indiana University Press, Bloomington, IN, USA, pp 403–417

    Google Scholar 

  • Ewing AW (1983) Functional aspects of Drosophila courtship. Biol Rev 58:275–292

    Google Scholar 

  • Ewing AW, Bennet-Clark HC (1968) The courtship song of Drosophila. Behaviour 31:287–301

    Google Scholar 

  • Fukushima K, Mayake S, Ito T (1983) Neocognitron: a neural network model for a mechanism of visual pattern recognition. IEEE Trans Syst Man Cybern SMC-13:826–834

    Google Scholar 

  • Gailey DA, Hall JC (1989) Behavior and cytogenetics of fruitless in Drosophila melanogaster: different courtship defects caused by separate, closely linked lesions. Genetics 121:773–785

    Google Scholar 

  • Gailey DA, Lacaillade, RC, Hall, JC (1986) Chemosensory elements of courtship in normal and mutant, olfaction-deficient Drosophila melanogaster. Behav Genet 16:375–405

    Google Scholar 

  • Gorczyca M, Hall JC (1987) The INSECTAVOX, an integrated device for recording and amplifying courtship songs. Drosophila Infor Serv 66:157–160

    Google Scholar 

  • Gorman RP, Sejnowski TJ (1988) Analysis of hidden units in a layered network trained to classify sonar targets. Neural Networks 1:75–89

    Google Scholar 

  • Greenspan RJ, Fin JA Jr, Hall JC (1980) Acetylcholinesterase mutants in Drosophila and their effects on the structure and function of the central nervous system. J Comp Neurol 189:741–774

    Google Scholar 

  • Grossberg S (1988) Nonlinear neural networks: Principles, mechanisms, architectures. Neural Networks 1:17–61

    Google Scholar 

  • Hall JC (1979) Control of the male reproductive behavior by the central nervous system of Drosophila: dissection of a courtship pathway by genetic mosaics. Genetics 92:437–457

    Google Scholar 

  • Hall JC (1986) Learning and rhythms in courting, mutant Drosophila. Trends Neurosci 9:414–418

    Google Scholar 

  • Hall JC, Kulkarni SJ, Kyriacou CP, Yu Q, Rosbash M (1990)Genetic and molecular analysis of neural development and behavior in Drosophila. In: Hahn ME, Hewitt JK, Henderson ND, Benno R (eds) Developmental behavioral genetics, Oxford University Press, New York, pp 100–112

    Google Scholar 

  • Haken H, Kelso JAS, Fuchs A, Pandya, AS (1990) Dynamic pattern recognition of coordinated biological motion. Neural Networks 3:395–401

    Google Scholar 

  • Hamblen M, Zehring WA, Kyriacou CP, Reddy P, Yu Q, Wheeler DA, Zwiebel LJ, Konopka RJ, Rosbash M, Hall JC (1986) Germ-line transformation involving DNA from the period locus of Drosophila melanogaster: overlapping genomic fragments that restore circadian and ultradian rhythmicity to per 0 and per − mutants. J Neurogenet 3:249–291

    Google Scholar 

  • Hopfield JJ, Tank DW (1985) Neural computations of decisions in optimization problems. Biol Cybern 52:141–152

    Google Scholar 

  • Hoy RR, Koikkala A, Kaneshiro K (1988) Hawaiian courtship songs: evolutionary innovations in communication signals of Drosophila. Science 240:217–219

    Google Scholar 

  • Hu MJC (1964) Application of the adaline system to weather forecasting. Tech Report 6775–1, Stanford Electronics Labs, Stanford, CA

    Google Scholar 

  • Jacobs RA (1988) Increased rates of convergence through learning rate adaption. Neural Networks 1:295–302

    Google Scholar 

  • Jolliffe IT (1986) Principal component analysis. Springer, New York Berlin Heidelberg

    Google Scholar 

  • Jones KR, Rubin GM (1990) Molecular analysis of no-on-transient A, a gene required for normal vision in Drosophila. Neuron 4:711–723

    Google Scholar 

  • Kohonen T, Barna G, Chrisley R (1988) Statistical pattern recognition with neural networks: benchmark studies. International Neural Network Society Proceeding, pp 61–68

  • Kohonen T (1987) Self organization and associative memory. Springer, New York Berlin Heidelberg

    Google Scholar 

  • rzanowski, WJ (1979) Between-groups comparison of principal components. J Am Statist Assoc 74:703–707 (Correction 76, 1022)

    Google Scholar 

  • Krzanowski, WJ (1982) Between-groups comparison of principal component — some sampling results. J Statist Computat Simul 15:141–154

    Google Scholar 

  • Kulkarni SJ, Hall JC (1987) Behavioral and cytogenetic analysis of the cacophony courtship song mutant and interacting genetic variants in Drosophila melanogaster. Genetics 115:461–475

    Google Scholar 

  • Kulkarni SJ, Steinlauf AF,Hall JC (1988) The dissonance mutant in Drosophila melanogaster: isolation, behavior, and cytogenetics. Genetics 118:267–285

    Google Scholar 

  • Kyriacou CP, Hall JC (1980) Circadian rhythm mutations in Drosophila affect short-term fluctuations in the male's courtship song. Proc Natl Acad Sci USA 77:6729–6733

    Google Scholar 

  • Kyriacou CP, Hall JC (1982) The function of courtship song rhythms in Drosophila. Anim Behav 30:794–801

    Google Scholar 

  • Kyriacou CP, Hall JC (1984) Learning and memory mutations impair acoustic priming of mating behavior in Drosophila. Nature 308:62–65

    Google Scholar 

  • Kyriacou CP, van den Berg MJ, Hall JC (1990) Drosophila courtship song cycles in normal and period mutant males revisited. Behav Genet 20:617–644

    Google Scholar 

  • Logan BF Jr (1977) Information in the zero-crossing of bandpass signals. Sys Tech J 56:487–510

    Google Scholar 

  • Makhoul J, Roucos S, Gish H (1986) Vector quantization in speech coding. Proc IEEE 73:1551–1587

    Google Scholar 

  • Mardia KV, Kent JT, Bibby JM (1979) Multivariate analysis. Academic Press, London

    Google Scholar 

  • Markow TA, Hanson SJ (1981) A multivariate analysis of Drosophila coursthip. Proc Natl Acad Sci USA 78:430–434

    Google Scholar 

  • Markow TA (1987) Behavior and sensory basis of coursthip success in Drosophila melanogaster. Proc Natl Acad Sci USA 84:6200–6204

    Google Scholar 

  • Menon MM, Heinemann KG (1988) Classification of patterns using a self-organizing neural network. Neural Networks 1:201–215

    Google Scholar 

  • Miyamoto H, Kawato M, Setoyama T, Suzuki R (1988) Feedback-error-learning neural network for trajectory control of a robotic manipulator. Neural Networks 1:251–265

    Google Scholar 

  • Neumann EK, Wheeler DA, Burnside JW, Bernstein AS, Hall JC (1990) A technique for the classification and analysis of insect courtship song. Proc Internat Joint Conf Neural Networks, vol II. International Neural Network Society IEEE, Lawrence Erlbaum Associates, Hilldale, NY, USA, pp 257–262

    Google Scholar 

  • Paulus MP, Geyer MA, Gold LH, Mandell AJ (1990) Application of entropy measures derived from the ergodic theory of dynamical systems to rat motor locomotor behavior. Proc Natl Acad Sci USA 87:723–727

    Google Scholar 

  • Rogers D (1989) Weather prediction using a genetic memory. In: Touretzky DS (eds) Neural information processing systems, vol 2. Morgan Kaufmann, San Mateo, CA, USA, pp 455–464

    Google Scholar 

  • Rosenberg CR, Sejnowski TJ (1987) Parallel networks that learn to pronounce English text. Complex Syst 1:145–168

    Google Scholar 

  • Rumelhart DE, McClelland J, the PDP Research Group (1986)Parallel distributed processing. MIT Press, Cambridge

    Google Scholar 

  • Schilcher Fv (1976a) The role of auditory stimuli in the courtship of Drosophila melanogaster. Anim Behav 24:18–26

    Google Scholar 

  • Schilcher Fv (1976b) The role of auditory stimuli in the courtship of Drosophila melanogaster. Anim Behav 24:622–625

    Google Scholar 

  • Schilcher Fv (1977) A mutation which changes courtship song in Drosophila melanogaster. Behav Genet 7:251–259

    Google Scholar 

  • Schilcher Fv, Hall JC (1979) Neural topography of courtship song in sex mosaics of Drosophila melanogaster. J. Comp Physiol 129:85–95

    Google Scholar 

  • Shannon CE (1948) The mathematical theory of communication. Bell Syst Tech J 27:379–423

    Google Scholar 

  • Siegel RW, Hall JC, Gailey DA, Kyriacou CP (1984) Genetic elements of courtship in Drosophila: mosaics and learning mutants. Behav Genet 14:383–410

    Google Scholar 

  • Skinner BF (1933) Analysis of inter-dependent behavioral components. J Gen Psychol 9:3–23

    Google Scholar 

  • Smith AW, Zipser D (1990) Encoding sequential structure: experience with the real-time recurrent learning algorithm. Proc Internat Joint Conf Neural Networks, vol I. International Neural Network Society IEEE, Lawrence Erlbaum Associates, Hilldale, NY, USA, pp 645–648

    Google Scholar 

  • Sokal RR, Rohlf FJ (1981) Biometry. Freeman, New York

    Google Scholar 

  • Spieth HT (1974) Courtship behavior in Drosophila. Ann Rev Entomol 19:385–406

    Google Scholar 

  • Tompkins L (1984) Genetic analysis of sex appeal in Drosophila. Behav Genet 14:411–440

    Google Scholar 

  • Webb AR, Lowe D (1990) The optimised internal representation of multilayer classifier networks performs nonlinear discriminant analysis. Neural Networks 3:367–375

    Google Scholar 

  • Werbos P (1984) Beyond regression: new tools for prediction and analysis in the behavioral sciences, Ph. D. Thesis, Harvard University, Cambridge, MA, USA

    Google Scholar 

  • Werbos P (1988) Generalization of backpropagation with application to a current gas market model. Neural Networks 1:21–29

    Google Scholar 

  • Wheeler DA, Fields WL, Hall JC (1988) Spectral analysis of Drosophila courtship Songs: D. melanogaster, D. simulans, and their interspecific hybrid. Behav Genet 18:675–703

    Google Scholar 

  • Wheeler DA, Klukarni SJ, Gailey DA, Hall JC (1989) Spectral analysis of courtship songs in behavioral mutants of Drosophila melanogaster. Behav Genet 19:503–528

    Google Scholar 

  • Widrow G, Hoff M (1960). Adaptive switching circuits. Institute of Radio Engineers, Western Electric Convention, part 4, pp 96–104

  • Yamamoto D, Sano Y, Ueda R, Togashi S, Tsumura S, Sato K (1991) Newly isolated mutants of Drosophila melanogaster defective in mating behavior (abstr). J Neurogenet 7:152

    Google Scholar 

Download references

Author information

Author notes

  1. Eric K. Neumann

    Present address: System and Technologies Division, Bolt, Beranek, and Newman, Inc, 02138, Cambridge, MA, USA

  2. David A. Wheeler

    Present address: Department of Cell Biology, Baylor College of Medicine, 77030, Houston, TX, USA

Authors and Affiliations

  1. Department of Biology, Brandeis University, 02254, Waltham, MA, USA

    Eric K. Neumann, David A. Wheeler, Adam S. Bernstein & Jeffrey C. Hall

  2. M.I.T. Lincoln Laboratory, 02173, Lexington, MA, USA

    Jamie W. Burnside

Authors
  1. Eric K. Neumann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David A. Wheeler
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adam S. Bernstein
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jamie W. Burnside
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jeffrey C. Hall
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Neumann, E.K., Wheeler, D.A., Bernstein, A.S. et al. Artificial neural network classification of Drosophila courtship song mutants. Biol. Cybern. 66, 485–496 (1992). https://doi.org/10.1007/BF00204113

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00204113

Keywords

Search

Navigation