Using spreadsheets as learning tools for neural network simulation

Abstract

The article supports the need for training techniques for neural network computer simulations in a spreadsheet context. Their use in simulating artificial neural networks is systematically reviewed. The authors distinguish between fundamental methods for addressing the issue of network computer simulation training in the spreadsheet environment, joint application of spreadsheets and tools for neural network simulation, application of third-party add-ins to spreadsheets, development of macros using 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 On the article, methods for creating neural network models in Google Sheets, a cloud-based spreadsheet, are discussed. The classification of multidimensional data presented in R. A. Fisher's "The Use of Multiple Measurements in Taxonomic Problems" served as the model's primary inspiration. Discussed are various idiosyncrasies of data selection as well as Edgar Anderson's participation in the 1920s and 1930s data preparation and collection. The approach of multi-dimensional data display in the form of an ideograph, created by Anderson and regarded as one of the first effective methods of data visualization, is discussed here.