English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The article substantiates the necessity to develop training methods ofcomputer simulation of neural networks in the spreadsheet environment. Thesystematic review of their application to simulating artificial neural networksis performed. The authors distinguish basic approaches to solving the problemof network computer simulation training in the spreadsheet environment, jointapplication of spreadsheets and tools of neural network simulation, applicationof third-party add-ins to spreadsheets, development of macros using theembedded languages of spreadsheets; use of standard spreadsheet add-ins fornon-linear optimization, creation of neural networks in the spreadsheetenvironment without add-ins and macros. After analyzing a collection ofwritings of 1890-1950, the research determines the role of the scientificjournal "Bulletin of Mathematical Biophysics", its founder Nicolas Rashevskyand the scientific community around the journal in creating and developingmodels and methods of computational neuroscience. There are identifiedpsychophysical basics of creating neural networks, mathematical foundations ofneural computing and methods of neuroengineering (image recognition, inparticular). The role of Walter Pitts in combining the descriptive andquantitative theories of training is discussed. It is shown that to acquireneural simulation competences in the spreadsheet environment, one should masterthe models based on the historical and genetic approach. It is indicated thatthere are three groups of models, which are promising in terms of developingcorresponding methods - the continuous two-factor model of Rashevsky, thediscrete model of McCulloch and Pitts, and the discrete-continuous models ofHouseholder and Landahl.

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