Computer Simulation of Neural Networks Using Spreadsheets: The Dawn of the Age of Camelot

Сергій Семеріков; Ілля Теплицький; Юлія Єчкало; Арнольд Ків

doi:10.31812/pedag.v51i0.3667

Authors

Сергій Семеріков Kryvyi Rih State Pedagogical University
Ілля Теплицький State Institution of Higher Education “Kryvyi Rih National University”
Юлія Єчкало State Institution of Higher Education “Kryvyi Rih National University”
Арнольд Ків Ben-Gurion University of the Negev, Beer Sheba, Israel

DOI:

https://doi.org/10.31812/pedag.v51i0.3667

Keywords:

computer simulation, neural networks, spreadsheets, neural computing, neuroengineering, computational neuroscience

Abstract

Semerikov S.O., Teplytsʹkyy I.O., Yechkalo YU.V. and Kiv A.E. Computer Simulation of Neural Networks Using Spreadsheets: The Dawn of the Age of Camelot.

The article substantiates the necessity to develop training methods of computer simulation of neural networks in the spreadsheet environment. The systematic review of their application to simulating artificial neural networks is performed. The authors distinguish basic approaches to solving the problem of network computer simulation training in the spreadsheet environment, joint application of spreadsheets and tools of neural network simulation, application of third-party add-ins to spreadsheets, development of macros using the embedded languages of spreadsheets; use of standard spreadsheet add-ins for non-linear optimization, creation of neural networks in the spreadsheet environment without add-ins and macros. After analyzing a collection of writings of 1890–1950, the research determines the role of the scientific journal “Bulletin of Mathematical Biophysics”, its founder Nicolas Rashevsky and the scientific community around the journal in creating and developing models and methods of computational neuroscience. There are identified psychophysical basics of creating neural networks, mathematical foundations of neural computing and methods of neuroengineering (image recognition, in particular). The role of Walter Pitts in combining the descriptive and quantitative theories of training is discussed. It is shown that to acquire neural simulation competences in the spreadsheet environment, one should master the models based on the historical and genetic approach. It is indicated that there are three groups of models, which are promising in terms of developing corresponding methods — the continuous two-factor model of Rashevsky, the discrete model of McCulloch and Pitts, and the discrete-continuous models of Householder and Landahl.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Abstract views: 204 / PDF downloads: 74

References

Abelson, H., Sussman, G. J., Sussman, J.: Structure and Interpretation of Computer Programs. 2nd edn. MIT Press, Cambridge (1996).

Abraham, T. H.: (Physio)logical circuits: The intellectual origins of the McCulloch-Pitts neural networks. Journal of the History of the Behavioral Sciences. 38 (1), 3–25 (2002). doi: 10.1002/jhbs.1094 DOI: https://doi.org/10.1002/jhbs.1094

Ayed, A. S.: Parametric Cost Estimating of Highway Projects using Neural Networks. Master thesis, Memorial University (1997).

Buergermeister, J. J.: Using Computer Spreadsheets for Instruction in Cost Control Curriculum at the Undergraduate Level. In: Dalton, D. W. (ed.) Restructuring Training and Education through Technology, Proceedings of the 32nd Annual Conference of the Association for the Development of Computer-Based Instructional Systems, San Diego, California, October 29 — November 1, 1990, pp. 214–220. ADCIS International, Columbus (1990).

Cowan, J. D. Interview with J. A. Anderson and E. Rosenfeld. In: Anderson, J. A., Rosenfeld, E. (eds.) Talking nets: An oral history of neural networks, pp. 97–124. MIT Press, Cambridge (1998).

Cull P.: The mathematical biophysics of Nicolas Rashevsky. BioSystems. 88 (3), 178–184 (2007). doi: 10.1016/j.biosystems.2006.11.003 DOI: https://doi.org/10.1016/j.biosystems.2006.11.003

Eberhart, R. C., Dobbins, R. W.: CHAPTER 1 — Background and History. In: Eberhart, R. C., Dobbins, R. W. (eds.) Neural Network PC Tools: A Practical Guide, pp. 9–34. Academic Press, San Diego (1990). DOI: https://doi.org/10.1016/B978-0-12-228640-7.50007-6

Freedman, R. S., Frail, R. P., Schneider, F. T., Schnitta, B.: Expert Systems in Spreadsheets: Modeling the Wall Street User Domain. In: Proceedings First International Conference on Artificial Intelligence Applications on Wall Street, Institute of Electrical and Electronics Engineers, New York, 9–11 Oct. 1991.

Hegazy, T., Ayed, A.: Neural Network Model for Parametric Cost Estimation of Highway Projects. Journal of Construction Engineering and Management. 124 (3), 210–218 (1998). doi: 10.1061/(ASCE)0733-9364(1998)124:3(210) DOI: https://doi.org/10.1061/(ASCE)0733-9364(1998)124:3(210)

Hewett, T. T.: Teaching Students to Model Neural Circuits and Neural Networks Using an Electronic Spreadsheet Simulator. Behavior Research Methods, Instruments, & Computers. 17 (2), 339–344 (1985). doi: 10.3758/BF03214406 DOI: https://doi.org/10.3758/BF03214406

Hewett, T. T.: Using an Electronic Spreadsheet Simulator to Teach Neural Modeling of Visual Phenomena (Report No. MWPS–F–85–1). Drexel University, Philadelphia (1985).

Householder, A. S., Landahl, H. D.: Mathematical Biophysics of the Central Nervous System. Principia Press, Bloomington (1945).

Householder, A. S.: A neural mechanism for discrimination: II. Discrimination of weights. Bulletin of Mathematical Biophysics. 2 (1), 1–13 (1940). doi: 10.1007/BF02478027 DOI: https://doi.org/10.1007/BF02478027

Householder, A. S.: A theory of steady-state activity in nerve-fiber networks III: The simple circuit in complete activity. Bulletin of Mathematical Biophysics. 3 (4), 137–140 (1941). doi: 10.1007/BF02477933 DOI: https://doi.org/10.1007/BF02477933

Householder, A. S.: A theory of steady-state activity in nerve-fiber networks IV. N circuits with a common synapse. Bulletin of Mathematical Biophysics. 4 (1), 7–14 (1942). doi: 10.1007/BF02477933 DOI: https://doi.org/10.1007/BF02477350

Householder, A. S.: A theory of steady-state activity in nerve-fiber networks I: Definitions and Preliminary Lemmas. Bulletin of Mathematical Biophysics. 3 (2), 63–69 (1941). doi: 10.1007/BF02478220 DOI: https://doi.org/10.1007/BF02478220

Householder, A. S.: A theory of steady-state activity in nerve-fiber networks II: The simple circuit. Bulletin of Mathematical Biophysics. 3 (3), 105–112 (1941). doi: 10.1007/BF02478168 DOI: https://doi.org/10.1007/BF02478168

Hryshchenko, N. V., Chernov, Ye. V., Semerikov, S. O.: Fizychni modeli v kursi “Osnovy kompiuternoho modeliuvannia” (Physical models in the course “Fundamentals of computer simulation”). In: Methodological and organizational aspects of the use of the INTERNET network in the institutions of science and education (INTERNET — EDUCATION — SCIENCE — 98), 1st international scientific and practical conference,

Vinnytsia, 1998, vol. 2, pp. 341–348. UNIVERSUM-Vinnytsia, Vinnytsia (1998).

James W.: Psychology. Henry Holt and Company, New York (1892).

James W.: The Principles of Psychology. Henry Holt and Company, New York (1890). DOI: https://doi.org/10.1037/10538-000

Johnston S. J.: Promised Land Comes Through With Braincel for Excel 3.0. InfoWorld. 13 (7), 14 (1991).

Kendrick, D. A., Mercado P. R., Amman H. M.: Computational Economics. Princeton University Press, Princeton (2006). DOI: https://doi.org/10.1515/9781400841349

Landahl, H. D., McCulloch, W. S., Pitts W.: A statistical consequence of the logical calculus of nervous nets. Bulletin of Mathematical Biophysics. 5 (4), 135–137 (1943). doi: 10.1007/BF02478260 DOI: https://doi.org/10.1007/BF02478260

Landahl, H. D., Runge, R.: Outline of a matrix calculus for neural nets. Bulletin of Mathematical Biophysics. 8 (2), 75–81 (1946). doi: 10.1007/BF02478464 DOI: https://doi.org/10.1007/BF02478464

Landahl, H. D.: A matrix calculus for neural nets: II. Bulletin of Mathematical Biophysics. 9 (2), 99–108 (1947). doi: 10.1007/BF02478296 DOI: https://doi.org/10.1007/BF02478296

McCulloch, W. C., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics. 5 (4), 115–133 (1943). doi: 10.1007/BF02478259 DOI: https://doi.org/10.1007/BF02478259

Mintii, I. S., Tarasov, I. V., Semerikov S. O.: Meta navchannia ta zmist kursu “Vstup do prohramuvannia” dlia maibutnikh uchyteliv informatyky (The purpose of the teaching and the contents of the

course “Introduction in programming” for future computer science teacher). Visnyk Cherkaskoho universytetu. Seriia pedahohichni nauky. 279, 57–63 (2013).

Mintii, I. S., Tarasov, I. V., Semerikov S. O.: Metodyka formuvannia u maibutnikh uchyteliv informatyky kompetentnostei z prohramuvannia na prykladi temy “Ekspertna systema” (Methods of forming

of future informatics teachers competencies in programming by example the theme “Expert system”). Naukovyi chasopys NPU im. M. P. Drahomanova. Seriia No2. Kompiuterno-oriientovani systemy navchannia. 14 (21), 91–96 (2014).

Permiakova, O. S., Semerikov, S. O.: Zastosuvannia neironnykh merezh u zadachakh prohnozuvannia (The use of neural networks in forecasting problems). In: Materials of the International Scientific and Practical

Conference “Young scientist of the XXI century”, KTU, Kryviy Rih, 17–18 November 2008.

Pitts, W., McCulloch, W. S.: How we know universals the perception of auditory and visual forms. Bulletin of Mathematical Biophysics. 9 (3), 127–147 (1947). doi: 10.1007/BF02478291 DOI: https://doi.org/10.1007/BF02478291

Pitts, W.: A general theory of learning and conditioning: Part I. Psychometrika. 8 (1), 1–18 (1943). doi: 10.1007/BF02288680 DOI: https://doi.org/10.1007/BF02288680

Pitts, W.: A general theory of learning and conditioning: Part II. Psychometrika. 8 (2), 131–140 (1943). doi: 10.1007/BF02288697 DOI: https://doi.org/10.1007/BF02288697

Pitts, W.: Some observations on the simple neuron circuit. Bulletin of Mathematical Biophysics. 4 (3), 121–129 (1942). doi: 10.1007/BF02477942 DOI: https://doi.org/10.1007/BF02477942

Pitts, W.: The linear theory of neuron networks: The dynamic problem. Bulletin of Mathematical Biophysics. 5 (1), 23–31 (1943). doi: 10.1007/BF02478116 DOI: https://doi.org/10.1007/BF02478116

Pitts, W.: The linear theory of neuron networks: The static problem. Bulletin of Mathematical Biophysics. 4 (4), 169–175 (1942). doi: 10.1007/BF02478112 DOI: https://doi.org/10.1007/BF02478112

Rapoport, A., Shimbel, A.: Steady states in random nets: I. Bulletin of Mathematical Biophysics. 10 (4), 211–220 (1948). doi: 10.1007/BF02477503 DOI: https://doi.org/10.1007/BF02477503

Rapoport, A.: Contribution to the probabilistic theory of neural nets: I. Randomization of refractory periods and of stimulus intervals. Bulletin of Mathematical Biophysics. 12 (2), 109–121 (1950). doi: 10.1007/BF02478248 DOI: https://doi.org/10.1007/BF02478248

Rapoport, A.: Contribution to the probabilistic theory of neural nets: II. Facilitation and threshold phenomena. Bulletin of Mathematical Biophysics. 12 (3), 187–197 (1950). doi: 10.1007/BF02478318 DOI: https://doi.org/10.1007/BF02478318

Rapoport, A.: Contribution to the probabilistic theory of neural nets: III. Specific inhibition. Bulletin of Mathematical Biophysics. 12 (4), 317–325 (1950). doi: 10.1007/BF02477902 DOI: https://doi.org/10.1007/BF02477902

Rapoport, A.: Contribution to the probabilistic theory of neural nets: IV. Various models for inhibition. Bulletin of Mathematical Biophysics. 12 (4), 327–337 (1950). doi: 10.1007/BF02477903 DOI: https://doi.org/10.1007/BF02477903

Rapoport, A.: Steady states in random nets: II. Bulletin of Mathematical Biophysics. 10 (4), 221–226 (1948). doi: 10.1007/BF02477504 DOI: https://doi.org/10.1007/BF02477504

Rashevsky, N.: Mathematical biophysics of abstraction and logical thinking. Bulletin of Mathematical Biophysics. 7 (3), 133–148 (1945). doi: 10.1007/BF02478314 DOI: https://doi.org/10.1007/BF02478314

Rashevsky, N.: Outline of a physico-mathematical theory of excitation and inhibition. Protoplasma. 20 (1), 42–56 (1933). doi: 10.1007/BF02674811 DOI: https://doi.org/10.1007/BF02674811

Rashevsky, N.: Some remarks on the boolean algebra of nervous nets in mathematical biophysics. Bulletin of Mathematical Biophysics. 7 (4), 203–211 (1945). doi: 10.1007/BF02478425 DOI: https://doi.org/10.1007/BF02478425

Rashevsky, N.: The neural mechanism of logical thinking. Bulletin of Mathematical Biophysics. 8 (1), 29–40 (1946). doi: 10.1007/BF02478425 DOI: https://doi.org/10.1007/BF02478469

Rienzo, T. F., Athappilly, K. K.: Introducing Artificial Neural Networks through a Spreadsheet Model. Decision Sciences Journal of Innovative Education. 10 (4), 515–520 (2012). doi: 10.1111/j.1540-4609.2012.00363.x DOI: https://doi.org/10.1111/j.1540-4609.2012.00363.x

Ruggiero M. A.: Cybernetic Trading Strategies: Developing a Profitable Trading System with State-of-the-Art Technologies. John Wiley & Sons, New York (1997).

Ruggiero, M.: Embedding neural networks into spreadsheet applications. US Patent 5,241,620, 31 Aug 1993.

Semerikov, S. O., Teplytskyi I. O.: Shtuchnyi intelekt v kursi informatyky pedahohichnoho VNZ (Artificial intelligence in teaching informatics at pedagogical university). In: Materials of the 4th All-Ukrainian Conference of Young Scientists on the Information Technologies in Education, Science and Technology ITONT–2004, Cherkasy, 28–30 April 2004.

Shimbel, A., Rapoport, A.: A statistical approach to the theory of the central nervous system. Bulletin of Mathematical Biophysics. 10 (2), 41–55 (1948). doi: 10.1007/BF02478329 DOI: https://doi.org/10.1007/BF02478329

Soloviov, V. M., Semerikov, S. O., Teplytskyi, I. O.: Instrumentalne zabezpechennia kursu kompiuternoho modeliuvannia (Instrumental computer simulation courseware). Kompiuter u shkoli ta simi. 4, 28–31 (2000).

Soloviov, V. M., Semerikov, S. O., Teplytskyi, I. O.: Osnovy kompiuternoho modeliuvannia v serednii shkoli ta pedahohichnomu vuzi (Fundamentals of computer simulation in secondary school and higher pedagogical institutions). In: Collection of scientific and practical materials of the All-Ukrainian conference on the Pre-professional training of pupils in the context of the implementation of the target comprehensive program “Teacher”, vol. 2, pp. 53–56. Dnipropetrovsk (1997).

Sussman, G. J., Wisdom, J.: Structure and interpretation of classical mechanics. 2nd edn. MIT Press, Cambridge (2015).

Teplytskyi, I., Semerikov, S.: Kompiuterne modeliuvannia mekhanichnykh rukhiv u seredovyshchi elektronnykh tablyts (Computer modeling of mechanical movements in an spreadsheets environment). Fizyka ta astronomiia v shkoli. 5, 41–46 (2002).

Teplytskyi, I. O., Semerikov, S. O.: Kompiuterna navchalna fizychna hra “Miaka posadka” (Computer training physical game “Soft landing”). Naukovi zapysky: zbirnyk naukovykh statei Natsionalnoho pedahohichnoho universytetu imeni M. P. Drahomanova. 53, 347–355 (2003).

Teplytskyi, I. O., Semerikov, S. O.: Kompiuterne modeliuvannia absoliutnykh ta vidnosnykh rukhiv planet Soniachnoi systemy (Computer simulation of absolute and relative motions of the planets the Solar system). Zbirnyk naukovykh prats Kamianets-Podilskoho natsionalnoho universytetu. Seriia pedahohichna. 13, 211–214 (2007).

Teplytskyi, I. O., Semerikov, S. O.: Modeliuvannia za dopomohoiu vypadkovykh chysel (Simulation using random numbers). Zbirnyk naukovykh prats Kamianets-Podilskoho natsionalnoho universytetu. Seriia pedahohichna. 17, 248–252 (2011).

Teplytskyi, I. O., Semerikov, S. O.: Na perekhresti ekolohii, matematyky, informatyky y fizyky (At the intersection of ecology, mathematics, computer science and physics). Zbirnyk naukovykh prats Kamianets-Podilskoho natsionalnoho universytetu. Seriia pedahohichna. 18, 34–37 (2012).

Teplytskyi, I. O.: Elementy kompiuternoho modeliuvannia (Elements of computer simulation). 2nd edn. KSPU, Kryvyi Rih (2010).

Teplytskyi, I. O.: Kompiuterne modeliuvannia v shkilnomu kursi informatyky (Computer simulation in the school informatics course). Nyva znan. Informatsiini tekhnolohii v osviti. 1, 63–74 (1994).

Teplytskyi, I. O.: Vykorystannia elektronnykh tablyts u kompiuternomu modeliuvanni (Using spreadsheets in computer simulation). Kompiuter u shkoli ta simi. 2, 27–32 (1999).

Wei, T.: On matrices of neural nets. Bulletin of Mathematical Biophysics. 10 (2), 63–67 (1948). doi: 10.1007/BF02477433 DOI: https://doi.org/10.1007/BF02477433

Weinberg, A. M.: Gale J. Young. Physics Today. 45 (1), 84 (1992). doi: 10.1063/1.2809507 DOI: https://doi.org/10.1063/1.2809507

Werbos, P. J.: Maximizing long-term gas industry profits in two minutes in Lotus using neural network methods. Transactions on Systems Man and Cybernetics. 19 (2), 315–333 (1989). doi: 10.1109/21.31036 DOI: https://doi.org/10.1109/21.31036

Yechkalo, Yu .V., Teplytskyi, I. O.: Kompiuterne modeliuvannia doslidu Rezerforda v seredovyshchi elektronnykh tablyts (Computer simulation of Rutherford’s experiment in a spreadsheet environment). In: Collection of scientific papers on the Modern technologies in science and education, vol. 2, pp. 56–59. KSPU Publishing department, Kryvyi Rih (2003).

Yechkalo, Yu. V.: Kompiuterne modeliuvannia brounivskoho rukhu (Computer simulation of the Brownian motion). Pedahohichnyi poshuk. 5, 97–100 (2010).

Yechkalo, Yu. V.: Kompiuterne modeliuvannia rukhu zariadzhenoi chastynky v mahnitnomu poli v seredovyshchi elektronnykh tablyts (Computer simulation of motion of a charged particle in a magnetic field in the environment of spreadsheets). Problemy suchasnoho pidruchnyka. 5 (2), 66–72 (2004).

Yechkalo, Yu. V.: Kompiuterne modeliuvannia yak zasib realizatsii mizhpredmetnykh zviazkiv kursu fizyky (Computer modeling as a means of realizing interdisciplinary connections in the physics course). Theory and methods of learning mathematics, physics, informatics. 5 (2), 125–128 (2005).

Yechkalo, Yu. V.: Tekhnolohiia navchannia kompiuternoho modeliuvannia fizychnykh protsesiv i yavyshch u starshii shkoli (Tech of learning of computer simulation of physical processes and phenomena in school). In: Abstracts of the 6th All-Ukrainian scientific and methodical workshop on the Computer modeling in education, Kryvyi Rih, 12 April 2013.

Yechkalo, Yu. V.: Vybir seredovyshcha modeliuvannia fizychnykh protsesiv (Selection of environment for simulation of physical processes). Theory and methods of learning mathematics, physics, informatics. 7 (2), 11–14 (2008).

Yechkalo, Yu. V.: Vykorystannia Dokumentiv Google dlia orhanizatsii spilnoi roboty zi stvorennia kompiuternoi modeli (The use of Google Docs to collaborate on the creation of computer model). In: Abstracts of the 5th All-Ukrainian scientific and methodical workshop on the Computer modeling in education, Kryvyi Rih, 6 April 2012.

Young, G.: On reinforcement and interference between stimuli. Bulletin of Mathematical Biophysics. 3 (1), 5–12 (1941). doi: 10.1007/BF02478102 DOI: https://doi.org/10.1007/BF02478102

Zaremba T.: CHAPTER 12 — Case Study III: Technology in Search of a Buck. In: Eberhart, R. C., Dobbins, R. W. (eds.) Neural Network PC Tools: A Practical Guide, pp. 251–283. Academic Press, San Diego (1990). DOI: https://doi.org/10.1016/B978-0-12-228640-7.50018-0