Impact of the compilation method on determining the accuracy of the error loss in neural network learning

Аkanova, Akerke; Kaldarova, Mira

doi:10.15587/2706-5448.2020.217613

Cited by 3 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further research should be aimed at reducing computational costs in processing various types of data in special-purpose information systems using artificial intelligence methods [25][26][27][28][29][30][31][32][33][34].…”

Section: Discussionmentioning

confidence: 99%

Development of object state estimation method in intelligent decision support systems

Bezuhlyi

Oliynyk

Romanenko

et al. 2021

EEJET

View full text Add to dashboard Cite

A method of object state estimation in intelligent decision support systems (DSS) has been developed. The essence of the method is to ensure a high-quality analysis of the current state of the analyzed object. The key difference of the developed method is the use of an advanced genetic algorithm. The advanced genetic algorithm is used when constructing a fuzzy cognitive model and increases the efficiency of identifying factors and relationships between them by simultaneously finding a solution by several individuals. The objective and complete analysis is achieved using advanced fuzzy temporal models of the object state, taking into account the type of uncertainty and noise of initial data. The method also contains an improved procedure for processing initial data under a priori uncertainty, an improved procedure for training artificial neural networks and an improved procedure for topological analysis of the structure of fuzzy cognitive models. The essence of the training procedure is the training of synaptic weights of the artificial neural network, the type and parameters of the membership function, as well as the architecture of individual elements and the architecture of the artificial neural network as a whole. The method increases the efficiency of data processing at the level of 11–15 % using additional advanced procedures. The proposed method can be used in DSS of automated control systems (artillery units, special-purpose geographic information systems). It can also be used in DSS for aviation and air defense ACS, as well as in DSS for logistics ACS of the Armed Forces

show abstract

Section: Discussionmentioning

confidence: 99%

Development of object state estimation method in intelligent decision support systems

Bezuhlyi

Oliynyk

Romanenko

et al. 2021

EEJET

View full text Add to dashboard Cite

show abstract

“…At this stage, the type of uncertainty about the analysis object state is taken into account and the basic model of the object state is initialized [21,31]. The degree of a priori uncertainty can be: full awareness; partial uncertainty; complete uncertainty.…”

Section: Development Of An Algorithm For Implementing the Methods Of Structural-parametric Assessment Of The Object Statementioning

confidence: 99%

“…Assume that for a system of any order, its coefficient at the highest degree is equal to 1, thus [19][20][21][22][23]:…”

Section: Formalized Description Of Structural and Parametric Assessment Of The Object Statementioning

confidence: 99%

Development of a method of structural-parametric assessment of the object state

Mahdi¹,

Zhyvotovskyi

Kravchenko

et al. 2021

EEJET

View full text Add to dashboard Cite

A method of structural and parametric assessment of the object state has been developed. The essence of the method is to provide an analysis of the current state of the object under analysis. The key difference of the developed method is the use of advanced procedures for processing undefined initial data, selection, crossover, mutation, formation of the initial population, advanced procedure for training artificial neural networks and rounding coordinates. The use of the method of structural-parametric assessment of the object state allows increasing the efficiency of object state assessment. An objective and complete analysis is achieved using an advanced algorithm of evolution strategies. The essence of the training procedure is the training of synaptic weights of the artificial neural network, the type and parameters of the membership function, the architecture of individual elements and the architecture of the artificial neural network as a whole. An example of using the proposed method in assessing the operational situation of the troops (forces) grouping is given. The developed method is 30–35 % more efficient in terms of the fitness of the obtained solution compared to the conventional algorithm of evolution strategies. Also, the proposed method is 20–25 % better than the modified algorithms of evolution strategies due to the use of additional improved procedures according to the criterion of fitness of the obtained solution. The proposed method can be used in decision support systems of automated control systems (artillery units, special-purpose geographic information systems). It can also be used in DSS for aviation and air defense ACS, DSS for logistics ACS of the Armed Forces of Ukraine

show abstract

“…Optimizing the compiler parameters, such as those governing loop unrolling, register allocation, or code generation, is another approach. The performance of an optimization strategy can be measured by its impact on the execution time, code size, energy cost, or, in the case of neural network compilers, the information loss [6]. The main focus has been on backend compiler optimization methods, such as scheduling, resource allocation [7], and code generation.…”

Section: Introductionmentioning

confidence: 99%

Constructing an AI Compiler for ARM Cortex-M Devices

Chang¹,

Hoang²

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

The diversity of software and hardware forces programmers to spend a great deal of time optimizing their source code, which often requires specific treatment for each platform. The problem becomes critical on embedded devices, where computational and memory resources are strictly constrained. Compilers play an essential role in deploying source code on a target device through the backend. In this work, a novel backend for the Open Neural Network Compiler (ONNC) is proposed, which exploits machine learning to optimize code for the ARM Cortex-M device. The backend requires minimal changes to Open Neural Network Exchange (ONNX) models. Several novel optimization techniques are also incorporated in the backend, such as quantizing the ONNX model's weight and automatically tuning the dimensions of operators in computations. The performance of the proposed framework is evaluated for two applications: handwritten digit recognition on the Modified National Institute of Standards and Technology (MNIST) dataset and model, and image classification on the Canadian Institute For Advanced Research and 10 (CIFAR-10) dataset with the AlexNet-Light model. The system achieves 98.90% and 90.55% accuracy for handwritten digit recognition and image classification, respectively. Furthermore, the proposed architecture is significantly more lightweight than other state-of-theart models in terms of both computation time and generated source code complexity. From the system perspective, this work provides a novel approach to deploying direct computations from the available ONNX models to target devices by optimizing compilers while maintaining high efficiency in accuracy performance.

show abstract

Impact of the compilation method on determining the accuracy of the error loss in neural network learning

Cited by 3 publications

References 2 publications

Development of object state estimation method in intelligent decision support systems

Development of object state estimation method in intelligent decision support systems

Development of a method of structural-parametric assessment of the object state

Constructing an AI Compiler for ARM Cortex-M Devices

Contact Info

Product

Resources

About