7 Reliable FPGA-Based Systems Out of Unreliable Automata: Multi-version Design Using Genetic Algorithms

Yakymets, Nataliya; Kharchenko, Vyacheslav

doi:10.1007/978-3-642-17545-9_7

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another interesting intersection of the artificial intelligence systems explainability problem and the theory of identification and diagnosis of machines is related to models of fully and partially defined and completely and partially correct digital machines [28]. This work defines the concept of a specified fully defined and partially correct automaton as having either fully predictable behavior, including known input sets or sequences on which the automaton operates incorrectly (does not correspond to the specified input-output transformations), or has unpredictable behavior on certain sets.…”

Section: Theory Of Machine Identification and Determination Of Condit...mentioning

confidence: 99%

Heuristic self-organization of knowledge representation and development: analysis in the context of explainable artificial intelligence

Dotsenko

Kharchenko

Morozova

et al. 2022

reks

Self Cite

View full text Add to dashboard Cite

From the analysis of the main theoretical provisions of heuristic self-organization systems and logical models, it follows that according to O. G. Ivakhnenko's systems of heuristic self-organization, the first task is to determine the factors content “that determine the essence of different images”. These are the images that characterize the objects of a particular subject area. After determining the composition and content of these images, the next problem is solved, namely, the problem of “generating the new successful heuristic”, which in content is a solution that leads to increased accuracy. Note that we are talking about improving the accuracy of solving the problem of data processing. It follows from the above mentioned that heuristic self-organization systems are data processing systems. This allows the multiplicity of heuristics. Heuristics in content correspond to the logical rules applied in heuristic self-organization systems. The main provisions of the heuristic self-organization system theory were developed by O. G. Ivakhnenko in the eighties of the last century, but they remain unnoticed to this day. At this time, the task is to explain why the neural network makes such a decision and not another. Based on this, the concept of “explainability of artificial intelligence” was introduced for artificial intelligence. It is the content of heuristics that forms the structure of the neural network in the form of logical rules and determines the logic of the decision made. It is established that the derivation rule, which is the basis for constructing artificial neural networks, is an abductive rule, which, unfortunately, does not meet the fourth heuristic and does not meet the definition of intelligence: intelligence is the ability to measure things. Unfortunately, none of the neural networks can measure things. From the analysis of the basic rules content of inference, it follows that the dialectical method of inference is general (generating) for the basic logical methods of inference. The difference lies in the composition and content of the middle member of the triangular relationship, namely, in the form of the element combination of the relationship: the transition from one concept to another. The explainability of artificial intelligence refers to the laws of the structure and activity of artificial neural networks. But modern theories of artificial neural networks ignore the existence of logical rules (heuristics), which were established by O. G. Ivakhnenko. After all, only knowing the rules based on which problems are solved, it is possible to check the correctness of the decision, but not by searching for such rules. The three hypotheses about the explainability of artificial intelligence and the theory of machine identification can be further defined as statements or theorems and strictly proved.

show abstract

Section: Theory Of Machine Identification and Determination Of Condit...mentioning

confidence: 99%

Heuristic self-organization of knowledge representation and development: analysis in the context of explainable artificial intelligence

Dotsenko

Kharchenko

Morozova

et al. 2022

reks

Self Cite

View full text Add to dashboard Cite

show abstract

“…The radial-basis function is specifically designed to estimate functions that are represented in the implicit form of a set of patterns. The neural network using these functions consists of one hidden layer, where only neurons in the hidden layer have a non-linear activation function [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Synthesis of the neuro-fuzzy regulator with genetic algorithm

Siddikov,

Porubay,

Rakhimov

2024

IJECE

View full text Add to dashboard Cite

Real-acting objects are characterized by the presence of various types of random perturbations, which significantly reduce the quality of the control process, which determines the use of modern methods of intellectual technology to solve the problem of synthesis of control systems of structurally complex dynamic objects, allowing to compensate the influence of external factors with the properties of randomness and partial uncertainty. The article considers issues of synthesis of the automatic control system of dynamic objects by applying the theory of intelligent control. In this case, a neural network based on radial-basis functions is used at each discrete interval for neuro-fuzzy approximation of the control system, allowing real-time adjustment of the regulator parameters. The radial basis function is designed to approximate functions defined in the implicit form of pattern sets. The neuro-fuzzy regulator's parameter configuration is accomplished using a genetic algorithm, enabling more efficient computation to determine the regulator's set parameters. The regulator's parameters are represented as a vector, facilitating their application to multidimensional objects. To determine the optimal tuning parameters of the neuro-fuzzy regulator, characterized by high convergence and the possibility of determining global extrema, a genetic algorithm was used. The effectiveness of the neuro-fuzzy regulator is explained by the possibility of providing quality control of the dynamic object under random perturbations and uncertainty of input data.

show abstract