Example of the Use of Artificial Neural Network in the Educational Process

Ibragim, Suleimenov; Akhat, Bakirov; Matrassulova, Dinara K.; Anastasiya, Grishina; Mariya, Kostsova; Grigoriy, Mun

doi:10.1007/978-3-030-39445-5_31

Cited by 7 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To simplify, one can say that 7 bits are used in order to convey the same amount of information that could be transmitted (with the deliberate absence of errors) using only 4 bits. From the point of view of set theory as shown in Figure 3, the use of error correction code can be interpreted as; the set A of all possible code combinations (in the example of the binary (7,4) Hamming code considered above-2 7 ) is divided into subsets A i , the number of which is equal to the number of code combinations r, treated as a code with an error corrected (in this example, 2 4 ). Any a ∈ A i is associated with a code combination with an absent error from the set B.…”

Section: Ann Research Methods By Comparison With Error-correcting Coding Algorithmsmentioning

confidence: 99%

“…Relationship (7) shows that for large 𝑁, the value log 2 𝑘, which determines the possibilities of information compression due to the factor of permissible errors, begins to depend on 𝑁 almost linearly. In particular, this means that an increase in the degree of information compression due to the factor of permissible errors with an increase in the number of symbols in a code sequence is achieved only at relatively small 𝑁.…”

Section: Analogue Of Shannon's Formula For Ann Without Feedbackmentioning

confidence: 99%

“…Thus, with 25% of permissible errors, 16-digit sequences can actually be transmitted by a 5-digit code, but for large 𝑁, the degree of information compression practically ceases to depend on 𝑁. Indeed, the ratio log 2 𝑘 𝑁 , can be taken as the degree of information compression, which, as shown in (7), remains constant with high accuracy at large 𝑁 In ( 12) admits a natural generalization to the case of any multiplier 𝑞specifying the percentage of acceptable errors; 𝑚 = 𝑞𝑁 Using again the Stirling formula for the asymptotic behavior of the binomial coefficient, we obtain…”

Section: Analogue Of Shannon's Formula For Ann Without Feedbackmentioning

confidence: 99%

“…Accordingly, the conclusions that are made in the neuroscience, as a rule, are the result of empirical generalization [7], i.e. most of the conclusions suffer from the same drawback as the conclusions that are made on a purely empirical basis, without the use of certain methodological concepts.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Distributed memory of neural networks and the problem of the intelligence`s essence

et al. 2022

View full text Add to dashboard Cite

The question of the nature of the distributed memory of neural networks is considered. Since the memory capacity of a neural network depends on the presence of feedback in its structure this question requires further study. It is shown that the neural networks without feedbacks can be exhaustively described based on analogy with the algorithms of noiseproof coding. For such networks the use of the term "memory" is not justified at all. Moreover, functioning of such networks obeys the analog of Shannon formula, first obtained in this paper. This formula allows to specify in advance the number of images that a neural network can recognize for a given code distance between them. It is shown that in the case of artificial neural networks with negative feedback it is really justified to talk about a distributed memory network. It is also shown that in this case the boundary between distributed memory of a neural network and information storage mechanisms in such elements as RS-triggers is diffuse. For the given example a specific formula is obtained, which connects the number of possible states of outputs of the network (and, hence, the capacity of its memory) with the number of its elements.

show abstract

Section: Ann Research Methods By Comparison With Error-correcting Coding Algorithmsmentioning

confidence: 99%

Section: Analogue Of Shannon's Formula For Ann Without Feedbackmentioning

confidence: 99%

Section: Analogue Of Shannon's Formula For Ann Without Feedbackmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Distributed memory of neural networks and the problem of the intelligence`s essence

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For example, Artificial Intelligence systems have a great impact on those who work in the commercial sphere, since AI-based systems allow you to access a large amount and quality of information in real time [12]. Another example of using AI is the creation of a neural network that processes students' critical reviews of pseudoscientific works, as well as identifies psychological personality types that are used to determine students who have the ability to work as a scientist [19].…”

Section: Introductionmentioning

confidence: 99%

Russia on the Global Artificial Intelligence Scene

Kochetkov

Birukou

Ermolayeva

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Artificial Intelligence (AI) is a very active research area with a number of applications in business, communication, healthcare, etc. AI attracts great attention in Russia and in late 2019 was included in the country strategy till 2030. In this paper we analyze Russia's position in the space of international scholarly publications on AI. While AI research is interdisciplinary, its core fits the computer science field, where most of the original results are published in conference proceedings and not in journals. Therefore, we consider the list of key AI conferences based on the Australian CORE and Microsoft Academic rankings. We conduct a comparative analysis Russia vs World based on the Scopus data. The metrics used in the analysis allow us to tackle both quantity and quality dimensions. The results of the study are essential for developing measures for the further implementation of the National Strategy for the Development of Artificial Intelligence in Russia and better understanding its position in the international scientific community.

show abstract

The Effectiveness of the Competence Approach in the Training of Chemistry Teachers

Abyzbekova,

Zholdasbayeva,

Tapalova

et al. 2023

J. Chem. Educ.

View full text Add to dashboard Cite

The most important problem for high-quality and effective education in a university is the creation of a set of competencies that reflect the results of the development of educational programs. The purpose of the study is to address the most important problem in achieving high-quality and effective education at a university, which is the development of a set of competencies reflecting the results of educational program development. The state educational standards for the educational program and the rules for drawing up the educational program were studied, and a review of the research of scientists on this problem and the work programs of various teachers of organic chemistry were conducted. The methods employed to determine the initial level of establishment of special and professional competencies among students of the educational programs 6B01515 "Chemistry" and 6B01516 "Chemistry-Biology" are specifically designed for the discipline of Organic Chemistry. These methods were

show abstract

Example of the Use of Artificial Neural Network in the Educational Process

Cited by 7 publications

References 1 publication

Distributed memory of neural networks and the problem of the intelligence`s essence

Distributed memory of neural networks and the problem of the intelligence`s essence

Russia on the Global Artificial Intelligence Scene

The Effectiveness of the Competence Approach in the Training of Chemistry Teachers

Contact Info

Product

Resources

About