USING MODULAR NEURAL NETWORKS AND MACHINE LEARNING WITH REINFORCEMENT LEARNING TO SOLVE CLASSIFICATION PROBLEMS
DOI:
https://doi.org/10.15588/1607-3274-2024-2-8Keywords:
modular neural networks, image classification, synthesis, diagnostics, topology, artificial intelligence, reinforcement learningAbstract
Context. The solution of the classification problem (including graphical data) based on the use of modular neural networks and modified machine learning methods with reinforcement for the synthesis of neuromodels that are characterized by a high level of accuracy is considered. The object of research is the process of synthesizing modular neural networks based on machine learning methods with reinforcement.
Objective is to develop a method for synthesizing modular neural networks based on machine learning methods with reinforcement, for constructing high-precision neuromodels for solving classification problems.
Method. A method for synthesizing modular neural networks based on a reinforcement machine learning approach is proposed. At the beginning, after initializing a system of modular neural networks built on the bottom-up principle, input data is provided – a training set of data from the sample and a hyperparameter to select the size of each module. The result of this method is a trained system of modular neural networks. The process starts with a single supergroup that contains all the categories of the data set. Then the network size is selected. The output matrix is softmax, similar to the trained network. After that, the average probability of softmax is used as a similarity indicator for group categories. If new child supergroups are formed, the module learns to classify between new supergroups. The training cycle of modular neural network modules is repeated until the training modules of all supergroups are completed. This method allows you to improve the accuracy of the resulting model.
Results. The developed method is implemented and investigated on the example of neuromodel synthesis based on a modular neural network for image classification, which can later be used as a model for technical diagnostics. Using the developed method significantly reduces the resource intensity of setting up hyperparameters.
Conclusions. The conducted experiments confirmed the operability of the proposed method of neuromodel synthesis for image classification and allow us to recommend it for use in practice in the synthesis of modular neural networks as a basis for classification models for further automation of tasks of technical diagnostics and image recognition using big data. Prospects for further research may lie in using the parallel capacities of GPU-based computing systems to organize directly modular neural networks based on them.
References
Kuo C. Transfer Learning for Image Classification: With Python Examples. New York, Kindle, 2022, 127 p.
Borra S., Thanki R., Dey N. Satellite Image Analysis: Clustering and Classification (SpringerBriefs in Applied Sciences and Technology). Cham, Springer, 2019, 113 p.
Siahaan V. Step by Step Tutorial image classification Using Scikit-Learn, Keras, And TensorFlow with Python. New York, Kindle, 2021, 141 p.
Canty M. J. Image Analysis, Classification and Change Detection in Remote Sensing: With Algorithms for Python. New York, CRC Press, 2019, 530 p.
Image Classification [Electronic resource]. Mode of access: https://www.sciencedirect.com/topics/engineering/imageclassification
Image Classification Explained [+V7 Tutorial] [Electronic resource]. Mode of access: https://www.v7labs.com/blog/image-classification-guide#h4
Image Classification in AI: How it works [Electronic resource]. Mode of access: https://levity.ai/blog/imageclassification-in-ai-how-it-works
Image Classification [Electronic resource]. Mode of access: https://huggingface.co/tasks/image-classification
Dayhoff J. Neural Network Architectures: An Introduction. New York, Van Nostrand Reinhold Company, 1990, 259 p.
Aggarwal C.C. Neural Networks and Deep Learning: A Textbook. Cham, Springer, 2018, 520 p.
Rashid T. Make Your Own Neural Network. CreateSpace Independent Publishing Platform, 2016, 222 p.
Jones H. Neural Networks: An Essential Beginners Guide to Artificial Neural Networks and their Role in Machine Learning and Artificial Intelligence. CreateSpace Independent Publishing Platform, 2018, 76 p.
Theobald O. Machine Learning for Absolute Beginners: A Plain English Introduction (Machine Learning with Python for Beginners). London, Scatterplot Press, 2020, 181 p.
Sebastian C. Machine Learning for Beginners: Absolute Beginners Guide, Learn Machine Learning and Artificial Intelligence from Scratch. New York, Kindle, 2018, 102 p.
Julian D. Designing Machine Learning Systems with Python. Birmingham, Packt Publishing, 2016, 232 p.
Burkov A. The Hundred-Page Machine Learning Book. New York, Kindle, 2022, 160 p.
Modular Neural Networks for Low-Power Image Classification on Embedded Devices [Electronic resource]. Mode of access: https://dl.acm.org/doi/10.1145/3408062
Reasoning Using Modular Neural Networks [Electronic resource]. Mode of access: https://towardsdatascience.com/reasoning-using-modularneural-networks-f003cb6109a2
What is a Modular Neural Network? Weak vs. Strong Learners [Electronic resource]. Mode of access: https://caseguard.com/articles/what-is-a-modular-neuralnetwork-weak-vs-strong-learners/
Modular neural networks using multiple gradients [Electronic resource]. Mode of access: http://essay.utwente.nl/82225/
The CIFAR-10 dataset [Electronic resource]. Mode of access: https://www.cs.toronto.edu/~kriz/cifar.html
The CIFAR-100 dataset [Electronic resource]. Mode of access: https://www.cs.toronto.edu/~kriz/cifar.html
CIFAR-100 [Electronic resource]. Mode of access: https://paperswithcode.com/dataset/cifar-100
The Street View House Numbers (SVHN) Dataset [Electronic resource]. Mode of access: http://ufldl.stanford.edu/housenumbers/
The EMNIST Dataset [Electronic resource]. Mode of access: https://www.nist.gov/itl/products-and-services/emnistdataset
ImageNet Large Scale Visual Recognition Challenge 2012 (ILSVRC2012) [Electronic resource]. Mode of access: https://www.image-net.org/challenges/LSVRC/2012/
Caltech 256 Image Dataset [Electronic resource]. Mode of access: https://www.kaggle.com/datasets/jessicali9530/caltech256
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 S. D. Leoshchenko, A. O. Oliinyk, S. A. Subbotin, T. O. Kolpakova
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
