System analysis of monitoring ecological information using Fuzzy ART neural network

In data analysis, presenting the boundaries between the classes of objects is considered a minor issue in most cases. However, the subsequent use of the analysis results (for example, in diagnostic tasks or in the acquisition of the necessary object properties by controlling the parameters) should be based on the boundaries delineation and the accuracy of their description. This underlines the need to develop and use universal methods for presenting the data analysis results. This paper considers the data model for applied decision support systems, in which one of the components is graphic data, i.e. domains in multidimensional space, bounded by general surfaces. A mathematical model is proposed, which outlines the range of possible graphic applications rather strictly. The paper proposes a meaningful approach to describing the boundaries delineation error. The material considered can serve as a basis for technology of data analysis results storage and use.

show abstract

Automation of the process of selecting hyperparameters for artificial neural networks for processing retrospective text information

Rogachev

Melikhova

2020

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Neural network technologies are successfully used in solving problems from various areas of the economy - industry, agriculture, medicine. The problems of substantiating the choice of architecture and hyperparameters of artificial neural networks (ins) aimed at solving various classes of applied problems are caused by the need to improve the quality and speed of deep ins training. Various methods of optimizing ins hyperparameters are known, for example, using genetic algorithms, but this requires writing additional software. To optimize the process of selecting hyperparameters, Google research has developed the KerasTuner Toolkit, which is a user-friendly platform for automated search for optimal hyperparameter combinations. In the described Kerastuner Toolkit, you can use random search, Bayesian optimization, or Hyperband methods. In numerical experiments, 14 hyperparameters varied: the number of blocks of convolutional layers and their forming filters, the type of activation functions, the parameters of the «dropout» regulatory layers, and others. The studied tools demonstrated high optimization efficiency while simultaneously varying more than a dozen parameters of the convolutional network, while the calculation time on the Colaboratory platform for the studied INM architectures was several hours, even with the use of GPU graphics accelerators. For ins focused on processing and recognizing text information in natural language (NLP), the recognition quality has been improved to 83-92%.

show abstract

System analysis of monitoring ecological information using Fuzzy ART neural network

Cited by 4 publications

References 5 publications

Computer Optimization of ANN Hyperparameters for Retrospective Information Processing

Computer Optimization of ANN Hyperparameters for Retrospective Information Processing

Representation of data analysis results in multidimensional parameter space

Automation of the process of selecting hyperparameters for artificial neural networks for processing retrospective text information

Contact Info

Product

Resources

About