Modeling of Intelligent Systems Architecture Based on the Brain Topology

2019 ◽  
pp. 267-279 ◽  
Author(s):  
Oleg Baranovski ◽  
Viktor Krasnoproshin ◽  
Alexander Valvachev
Keyword(s):  
Intelligent Systems ◽  
Systems Architecture ◽  
The Brain

Something Old, Something New, Something Borrowed, Something Blue: Part 3 – An Elephant Never Forgets

2017 ◽  
Vol 26 (3) ◽  
pp. 433-437
Author(s):  
Mark Dougherty
Keyword(s):  
Artificial Intelligence ◽  
Intelligent Systems ◽  
Natural Systems ◽  
European Court ◽  
New Knowledge ◽  
The Right ◽  
Contextual Environment ◽  
The Brain ◽  
Index Services ◽  
Incomplete Picture

AbstractForgetting is an oft-forgotten art. Many artificial intelligence (AI) systems deliver good performance when first implemented; however, as the contextual environment changes, they become out of date and their performance degrades. Learning new knowledge is part of the solution, but forgetting outdated facts and information is a vital part of the process of renewal. However, forgetting proves to be a surprisingly difficult concept to either understand or implement. Much of AI is based on analogies with natural systems, and although all of us have plenty of experiences with having forgotten something, as yet we have only an incomplete picture of how this process occurs in the brain. A recent judgment by the European Court concerns the “right to be forgotten” by web index services such as Google. This has made debate and research into the concept of forgetting very urgent. Given the rapid growth in requests for pages to be forgotten, it is clear that the process will have to be automated and that intelligent systems of forgetting are required in order to meet this challenge.

scholarly journals An intelligent systems architecture for manufacturing (ISAM):

2002 ◽  
Author(s):  
J S Albus ◽  
H A Scott ◽  
E Messina ◽  
H M Huang ◽  
A J Horst ◽  
...  
Keyword(s):  
Intelligent Systems ◽  
Systems Architecture

The Cognitive Process of Comprehension

2010 ◽  
Vol 4 (3) ◽  
pp. 44-58 ◽  
Author(s):  
Yingxu Wang ◽  
Davrondzhon Gafurov
Keyword(s):  
Cognitive Processes ◽  
Intelligent Systems ◽  
Cognitive Process ◽  
Process Algebra ◽  
Formal Model ◽  
Reference Model ◽  
Process Models ◽  
Abstract Thought ◽  
Comprehension Process ◽  
The Brain

Comprehension is an ability to understand the meaning of a concept or an action. Comprehension is an important intelligent power of abstract thought and reasoning of humans or intelligent systems. It is highly curious to explore the internal process of comprehension in the brain and to explain its basic mechanisms in cognitive informatics and computational intelligence. This paper presents a formal model of the cognitive process of comprehension. The mechanism and process of comprehension are systematically explained with its conceptual, mathematical, and process models based on the Layered Reference Model of the Brain (LRMB) and the Object-Attribute-Relation (OAR) model for internal knowledge representation. Contemporary denotational mathematics such as concept algebra and Real-Time Process Algebra (RTPA) are adopted in order to formally describe the comprehension process and its interaction with other cognitive processes of the brain.

Intelligent Traffic Sign Classifiers

2011 ◽  
pp. 956-962
Author(s):  
Raúl Vicen Bueno ◽  
Elena Torijano Gordo ◽  
Antonio García González ◽  
Manuel Rosa Zurera ◽  
Roberto Gil Pita
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Intelligent Systems ◽  
Main Part ◽  
Point Of View ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Artificial Neural ◽  
The Brain

The Artificial Neural Networks (ANNs) are based on the behavior of the brain. So, they can be considered as intelligent systems. In this way, the ANNs are constructed according to a brain, including its main part: the neurons. Moreover, they are connected in order to interact each other to acquire the followed intelligence. And finally, as any brain, it needs having memory, which is achieved in this model with their weights. So, starting from this point of view of the ANNs, we can affirm that these systems are able to learn difficult tasks. In this article, the task to learn is to distinguish between different kinds of traffic signs. Moreover, this ANN learning must be done for traffic signs that are not in perfect conditions. So, the learning must be robust against several problems like rotation, translation or even vandalism. In order to achieve this objective, an intelligent extraction of information from the images is done. This stage is very important because it improves the performance of the ANN in this task.

Intelligent Radar Detectors

2011 ◽  
pp. 933-939
Author(s):  
Raúl Vicen Bueno ◽  
Manuel Rosa Zurera ◽  
María Pilar Jarabo Amores ◽  
Roberto Gil Pita ◽  
David de la Mata Moya
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Intelligent Systems ◽  
Main Part ◽  
Point Of View ◽  
Communications Systems ◽  
Reflected Signal ◽  
Artificial Neural ◽  
The Brain

The Artificial Neural Networks (ANNs) are based on the behaviour of the brain. So, they can be considered as intelligent systems. In this way, the ANNs are constructed according to a brain, including its main part: the neurons. Moreover, they are connected in order to interact each other to acquire the followed intelligence. And finally, as any brain, it needs having memory, which is achieved in this model with their weights. So, starting from this point of view of the ANNs, we can affirm that these systems are able to learn difficult tasks. In this article, the task to learn is to distinguish between the presence or not of a reflected signal called target in a Radar environment dominated by clutter. The clutter involves all the signals reflected from other objects in a Radar environment that are not the desired target. Moreover, the noise is considered in this environment because it always exists in all the communications systems we can work with.

Artificial Neural Networks for Prediction

2011 ◽  
pp. 54-58
Author(s):  
Rafael Marti
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Intelligent Systems ◽  
Intelligent System ◽  
Human Capabilities ◽  
Design And Implementation ◽  
Starting Point ◽  
Input Signals ◽  
Artificial Neural ◽  
The Brain

The design and implementation of intelligent systems with human capabilities is the starting point to design Artificial Neural Networks (ANNs). The original idea takes after neuroscience theory on how neurons in the human brain cooperate to learn from a set of input signals to produce an answer. Because the power of the brain comes from the number of neurons and the multiple connections between them, the basic idea is that connecting a large number of simple elements in a specific way can form an intelligent system.

scholarly journals Development of a structural diagram of a cognitive transport system

2021 ◽  
pp. 166-174
Author(s):  
С.А. Селиверстов ◽  
Я.А. Селиверстов ◽  
А.Г. Котенко ◽  
О.Ю. Лукомская ◽  
Н.В. Шаталова ◽  
...  
Keyword(s):  
Transport System ◽  
Intelligent Systems ◽  
Cognitive Architecture ◽  
Unmanned Vehicles ◽  
Transport Systems ◽  
Structural Diagram ◽  
Cognitive Architectures ◽  
Transport Control ◽  
The Subject ◽  
The Brain

Развитие технологий проектирования интеллектуальных систем, использующих алгоритмы схожие с мыслительной обработкой мозга, стимулируют поиски новых подходов для создания искусственного интеллекта человеческого уровня. Для выполнения столь сложных задач используются когнитивные архитектуры, представляя собой следующий уровень развития разнородных процессов интеллектуализации. В данной статье под практической призмой интеллектуализации транспортных систем исследуется процесс развития современных когнитивных архитектур. Предметом исследования является разработка структурной схемы когнитивной транспортной системы. Для выполнения этой задачи исследуются новые парадигмы когнитивного управления, расширяющие подходы к вычислительному интеллекту. Уточняется понятие когнитивной архитектуры. Исследуются современные работы в области каталогизации когнитивных архитектур. Выявляются критерии оценки когнитивных архитектур. Подробно рассматриваются и анализируются когнитивные архитектуры 4D / RCS, ALLIANCE, LIDA, использующиеся в современных системах управления беспилотным транспортом и роботами. Выявляются положительные обобщенные факторы, направленные на эффективность когнитивной архитектуры. Разрабатывается структурная схема когнитивной транспортной системы, основные подсистемы которой включают когнитивное управление транспортом, когнитивные транспортные коммуникации, когнитивные транспортные средства. Описывается структура слоев. Отмечаются преимущества, в том числе бионинспирированность, модульность, объектно-ориентированность, параллелизм, возможность использования интеллектуальных методов обучения. The development of technologies for the design of intelligent systems using algorithms similar to mental processing of the brain stimulates the search for new approaches to create artificial intelligence at the human level. To perform such complex tasks, cognitive architectures are used, representing the next level of development of heterogeneous intellectualization processes. In this article, under the practical prism of intellectualization of transport systems, the process of development of modern cognitive architectures is investigated. The subject of the research is the development of a structural diagram of the cognitive transport system. To accomplish this task, new paradigms of cognitive control are being investigated, expanding approaches to computational intelligence. The concept of cognitive architecture is clarified. Examines current work in the field of cataloging cognitive architectures. Criteria for assessing cognitive architectures are identified. Cognitive architectures 4D / RCS, ALLIANCE, LIDA, used in modern control systems for unmanned vehicles and robots, are considered and analyzed in detail. We identify positive generalized factors aimed at the effectiveness of cognitive architecture. A structural diagram of the cognitive transport system is being developed, the main subsystems of which include cognitive transport control, cognitive transport communications, and cognitive vehicles. The structure of the layers is described. The advantages are noted, including bioninspiration, modularity, object-orientation, parallelism, the possibility of using intelligent teaching methods.

Sign in / Sign up

Export Citation Format

Share Document