FEDERAL AGENCY FOR EDUCATION
STATE EDUCATIONAL INSTITUTION
HIGHER PROFESSIONAL EDUCATION
"VOLGOGRAD STATE TECHNICAL UNIVERSITY"
KAMYSHIN TECHNOLOGICAL INSTITUTE (BRANCH)
GOU VPO "VOLGOGRAD STATE TECHNICAL UNIVERSITY"
PRACTICAL COURSE IN THE DISCIPLINE “ARTIFICIAL INTELLIGENCE SYSTEMS”
Educational electronic edition
Volgograd
NL – natural language
AI – artificial intelligence
LP – predicate logic
Decision maker - decision maker
MT – Turing machine
PGA – simple genetic algorithm
PPF - a correctly constructed formula
PRO – primitive recursive operator
PRF – primitive recursive function
RF – recursive function
SNI – artificial intelligence system
FP – fitness function
TF - objective function
ES – expert system
INTRODUCTION
Initially, artificial intelligence was seen as the science of creating thinking machines. This field was considered the holy grail of computer science. Over time, artificial intelligence has evolved into a more pragmatic discipline. This area still includes the study of the mechanisms of thinking. Within the framework of artificial intelligence, various strategies for computer solving complex practical problems are considered. In addition, today it has become clear that intelligence itself is too complex an entity that cannot be described within the framework of one theory. Various theories describe it at different levels of abstraction. Learning at the lowest level is provided by neural networks, recognition machines, genetic algorithms, and other forms of computing that model the ability to adapt, perceive, and interact with the physical world. At a higher level of abstraction, the creators of expert systems, intelligent agents, stochastic models and natural language understanding systems work. This level takes into account the role of social processes in the creation, transmission and retrieval of knowledge. The highest level of abstraction includes logical approaches, including deductive, abductive models, truth support systems and other forms and methods of reasoning.
This manual outlines the basics of some low-level theories with practical tasks for studying algorithms based on the provisions of these theories. In particular, the foundations of the theory of pattern recognition are considered with the task of studying linear discriminant functions and similarity functions; theory of artificial neural networks with the formulation of the problem of studying the properties of artificial neural networks on the problem of pattern recognition; genetic algorithms with the formulation of the problem of studying their properties when searching for the extremum of a function. To perform research tasks, you must be able to program in some programming language, preferably object-oriented.
1.1. Origin of the theory of artificial intelligence
1.1.1. Artificial intelligence concept
Term intelligence(intelligence) comes from the Latin intellectus, which means mind, reason, mind, and the thinking abilities of a person. Respectively artificial intelligence(AI, in English equivalent: artificial intelligence, AI) is the property of automatic systems to take on individual functions of human intelligence.
Any artificial intelligence is a model of decision-making carried out by the natural intelligence of a person. Artificial intelligence can qualify for comparison with natural intelligence, provided that the quality of the solutions generated is no worse than average natural intelligence.
1.1.2. Artificial intelligence in the automation loop
In such systems, the control loop is introduced decision maker(DM).
The decision maker has his own system of preferences regarding the criterion for managing the object, and even the purpose of the object’s existence. The decision maker, most often, does not agree, at least partially, with the modes offered by the traditional automated control system. The decision maker, as a rule, controls the main parameters of the system, while the rest is controlled by local control systems. The task arises of automating the activities of decision makers in the control loop.
AI is a research area that creates models and corresponding software that allow computers to solve problems of a creative, non-computational nature, which in the solution process require addressing semantics (the problem of meaning).
AI is a software system that imitates human thinking on a computer. To create such a system, it is necessary to study the decision-maker’s thinking process, highlight the main steps of this process, and develop software that reproduces these steps on a computer.
1.1.3. The concept of intellectual task and activity
A feature of human intelligence is the ability to solve intellectual problems by acquiring, memorizing and purposefully transforming knowledge in the process of learning from experience and adapting to a variety of circumstances.
Intellectual tasks– problems, the formal division of the process of finding a solution for which into separate elementary steps often turns out to be very difficult, even if their solution itself is not difficult.
We will call brain activity aimed at solving intellectual problems thinking or intellectual activity.
Intellectual activity presupposes the ability to infer, generate, and construct a solution that is not explicitly and ready-made in the system. Conclusion of solutions is possible only if there is an internal representation of knowledge in the system ( models of the outside world) – a formalized representation of knowledge about the external world (automated subject area).
1.1.4. The first steps in the history of artificial intelligence
The first programs implementing the features of intellectual activity:
1. Machine translation (1947). In the USSR, since 1955, work in the field of machine translation has been associated with... The task of machine translation required separating knowledge from code. The appearance of an intermediary language marked the first attempt to create a language for the internal representation of knowledge.
2. Automated abstracting and information retrieval (1957, USA). The idea of isolating a system of connections and relationships between individual facts, embodied in the concept of a thesaurus.
3. Proof of theorems (1956, USA). The emergence of a program for proving propositional logic theorems: “Logician-Theorist”. In 1965, the resolution method appeared (J. Robinson, USA), in 1967 - the reverse method (USSR). Methods implement the idea of using heuristic– experienced rules to reduce the search for options when deriving a solution.
4. Pattern recognition (early 60s). Ideas in recognition theory related to learning to find the decisive rule from a set of positive and negative examples.
In 1956, K. Shannon, M. Minsky and J. McCarthy organized a conference in Dartmouth (USA) to summarize practical experience in the development of intelligent programs.
1.1.5. Creation of a theoretical basis
In 1969, the First International Conference on Artificial Intelligence (IJCAI) was held in Washington. In 1976, the international journal Artificial Intelligence began publishing. During the 70s, the main theoretical directions of research in the field of intelligent systems emerged:
− knowledge representation, formalization of knowledge about the external environment, creation of an internal model of the external world;
− communication, creation of languages for interaction between the system and the user;
− reasoning and planning, decision-making in alternative situations;
− perception (machine vision), obtaining data from the external environment;
− training, extracting knowledge from the experience of the system;
− activity, active behavior of the system based on its own operating goals.
1.1.6. Philosophical problems theories of artificial intelligence
This subsection lists the main questions and some comments on them on frequently and widely discussed problems in the theory of artificial intelligence.
Is it possible to reproduce intelligence? Self-reproduction is theoretically possible. The fundamental possibility of automating the solution of intellectual problems using a computer is ensured by the property of algorithmic universality. However, one should not think that computers and robots can, in principle, solve any problem. There are algorithmically unsolvable problems.
What is the goal of creating artificial intelligence? Let us assume that a person has managed to create an intellect that exceeds his own intellect (even if not in quality, but in quantity). What will happen to humanity now? What role will the person play? What is it used for now? And in general, is it necessary to create AI in principle? Apparently, the most acceptable answer to these questions is the concept of an “intelligence enhancer.”
Is it safe to create artificial intelligence? Possessing intelligence and communication capabilities many times greater than those of humans, technology will become a powerful independent force capable of counteracting its creator.
1.1.7. Areas of use
1. Processing of natural languages, recognition of images, speech, signals, as well as the creation of intelligent interface models, financial forecasting, data extraction, system diagnostics, monitoring network activities, data encryption (direction - neural networks).
2. Nanotechnology, problems of self-assembly, self-configuration and self-healing of systems consisting of many simultaneously functioning nodes, multi-agent systems and robotics (direction - evolutionary calculations).
3. Hybrid control systems, image processing, tools for searching, indexing and analyzing the meaning of images, recognition and classification of images (direction - fuzzy logic).
4. Medical diagnostics, training, consulting, automatic programming, testing and analysis of program quality, design of ultra-large integrated circuits, technical diagnostics and development of recommendations for equipment repair, planning in various subject areas and data analysis (direction - expert systems (ES)).
5. Transport tasks, distributed computing, optimal resource loading (direction - methods for reducing search).
6. Development of large software design systems, code generation, verification, testing, quality assessment, identifying the possibility of reuse, solving problems on parallel systems (direction - intelligent engineering).
7. Creation of fully automated cyber factories.
8. Games, social behavior of human emotions, creativity.
9. Military technologies.
1.2. Architecture of artificial intelligence systems
1.2.1. Elements of ASI architecture
Artificial Intelligence System Architecture(SII) – organization of the structure within which decision-making and application of knowledge in a specific area occur. The most general scheme of SII is presented in Fig. 1. Not a single real AI exists in this form; certain blocks may be missing. In AIS there are always only two blocks: the knowledge base and the inference mechanism.
Let's consider the main types of artificial intelligence in automated information processing and control systems:
− SII for technological process control;
− SII diagnostics;
− SII planning and dispatching;
− intelligent robots.
https://pandia.ru/text/78/057/images/image005_133.gif" width="357" height="360 src=">
Rice. 1. Generalized scheme of AIS
1.2.2. SII process control
The architecture of the automated process control information system is shown in Fig. 2.
Features of this system:
− use of technological information for management (measured product characteristics about the parameters and structure of equipment);
− the inference mechanism is used to modify data and develop recommendations and management decisions;
− the need to work in real time;
− the need to implement temporal reasoning (taking into account changing conditions).
The system operates at three levels:
− the knowledge base (KB) includes rules for solving problems, procedures for solving problems, data about the problem area, that is, the technology itself and the entire process management strategy are organized at the level of knowledge bases;
− working memory contains information about specified characteristics and data about the process under consideration (DB);
− the output mechanism (in a conventional system is a regulator) contains a general control mechanism to achieve the final goal (an acceptable solution).
An important component is the communication blocks between the technological process with the database and knowledge base (blocks “Data Analysis” and “Process Data”). They provide the user with a top-level access to production information about the technological process from lower-level objects, i.e., they keep the contents of the database and knowledge base up to date by updating. The units also provide monitoring functions to prevent critical situations.
Justification and explanation of the balance and adequacy of the system’s response to the development of the production situation is provided by the “Dialogue Interface” and “Control Data” blocks.
https://pandia.ru/text/78/057/images/image007_118.gif" width="357" height="149 src=">
Rice. 2. Structure of automated control systems for technological process control
1.2.3. SII diagnostics
This system is basically no different from the previous system. And since the signs of various defects may largely coincide and their manifestations may not be constant, these systems contain more comprehensive components of substantiation and explanation of the diagnosis. Therefore, very often in such systems, decisions are assessed from the point of view of subjective probability.
1.2.4. SII of robotic lines and flexible production systems
A feature of such systems is the presence of a world model. A robotic system operates in its own specific environment, and a detailed description of this environment is in principle possible. This mathematical model environment is called model of the outside world. It is the main content of the knowledge base of the AI robot, and another part of the knowledge base is knowledge about the goals of the system (Fig. 3).
https://pandia.ru/text/78/057/images/image009_112.gif" width="294" height="100 src=">
Rice. 3. SII robotic lines and flexible production systems
The system for perceiving the state of the environment includes:
− sensors directly connected with the external environment;
− pre-processing subsystem;
− characteristic features segmentation block;
− symbolic description of the state of the environment;
− semantic description of the state of the environment;
− block for forming a model of the state of the environment.
The inference mechanism or behavior planning system determines the robot's actions in the external environment as a result of the current situation and in accordance with the global goal. Comprises:
− decision output systems;
− unit for planning the movement of actuators.
The action execution system includes:
− drive control subsystem;
− drive;
− actuators.
1.2.5. SII planning and dispatching
Purpose: solve problems of operational management, comparison of the results of monitoring the functioning of an object in terms of planned tasks, as well as monitoring (Fig. 4).
Monitoring– continuous or periodic interpretation of signals and issuance of messages when situations arise that require intervention.
The peculiarity of these systems is real-time action, communication with a distributed database of an integrated control system. Such a system is necessary since AIS data is part of control systems.
https://pandia.ru/text/78/057/images/image011_89.gif" width="365" height="167 src=">
Rice. 4. SII planning and dispatching
1.3. The problem of knowledge representation in AIS
1.3.1. Knowledge and data
The problem of knowledge representation arose as one of the problems of AI. It is associated with the creation of practically useful systems, primarily ES, used in medicine, geology, and chemistry. The creation of such systems requires intensive efforts to formalize the knowledge accumulated in the relevant science.
The term “knowledge representation” is associated with a certain stage in the development of computer software. If at the first stage programs dominated, and data played an auxiliary role as a kind of “food” for “hungry” programs, then at subsequent stages the role of data steadily increased. Their structure became more complex: from a machine word located in one computer memory cell, there was a transition to vectors, arrays, files, and lists. The culmination of this development was abstract data types - classes. The consistent development of data structures has led to their qualitative change and to the transition from data representation to knowledge representation.
acquisition of knowledge
The level of knowledge representation differs from the level of data representation not only in its more complex structure, but also in significant features: interpretability, the presence of classifiable connections, the presence situational relationships(simultaneity, being at one point in space, etc., these relationships determine the situational compatibility of certain knowledge stored in memory). In addition, the level of knowledge is characterized by such features as the presence of special procedures for generalization, replenishment of knowledge available in the system, and a number of other procedures.
Data presentation has a passive aspect: a book, a table, a memory filled with information. AI theory emphasizes the active aspect of knowledge representation: acquisition of knowledge should become an active operation that allows not only to remember, but also to apply the perceived (acquired, assimilated) knowledge for reasoning based on it.
1.3.2. The idea of self-developing machines
Research in the field of AI arose under the influence of the ideas of cybernetics - primarily the idea of the commonality of processes for controlling and transmitting information in living organisms, society and technology, in particular in computers.
The philosophical acceptability of the AI problem in its traditional form was due to the underlying idea that the order and connection of ideas are the same as the order and connection of things. Thus, creating a structure in a computer that reproduces the “world of ideas” simply meant creating a structure isomorphic to the structure of the material world, i.e., building an “electronic model of the world.” This model was considered as a computer model - a model of human knowledge about the world. The process of human thinking was interpreted in the computer as a machine search for such model transformations that were supposed to transfer the computer model to a certain final state. AGI needed knowledge of how to carry out transformations of model states leading to a predetermined goal - a state with certain properties. At first, there was a widespread belief in the fundamental ability of a computer to independently study the model stored in it, that is, to self-teach a strategy for achieving a set goal.
This hypothetical ability was interpreted as the possibility of machine creativity, as the basis for the creation of future “thinking machines.” And although in the systems actually being developed, the goal was achieved on the basis of human experience with the help of algorithms based on a theoretical analysis of the models being created and the results of experiments conducted on them, the ideas of building self-learning systems seemed to many to be the most promising. Only by the 1980s was the significance of the problem of using human knowledge about reality in intelligent systems realized, which led to the serious development of knowledge bases and methods for extracting personal knowledge of experts.
1.3.3. Reflection as a component of intellectual activity
With the development of this direction, the idea of reflexive management arose. Until this point, in cybernetics, control was considered as the transmission of signals to an object that directly affect its behavior, and the effectiveness of control was achieved through feedback - obtaining information about the reactions of the controlled object. Reflexive same control– is the transfer of information that affects the object’s image of the world. Thus, feedback turns out to be unnecessary - the state of the subject is known to the transmitter of information, that is, to the object.
Traditional AGIs are based on the ideology of goal-oriented behavior such as a chess game, where the goal of both partners is to checkmate at the cost of any sacrifice. It is no coincidence that chess programs turned out to be so important for developing AI methods.
Analysis of the functioning of one’s own model or the model of “the entire surrounding reality” (within the framework of the task), control over its state, forecasting the state is nothing more than the implementation of reflection. Reflection is a certain meta-level. With the use of high-level programming languages, such as Prolog, which allows you to formulate goals and build logical conclusions about the achievability of these goals, the task of implementing reflection can already be partially solved. With their help, you can build a certain superstructure, a certain meta-level that allows you to evaluate the behavior of the previous one. However, when considering the term “deep reflection” or “multi-level reflection”, the problem of constructing models by the system itself arises. This is where abstract data types come to the rescue. They allow you to operate with data structures of any finite complexity. Thus, we can consider that artificial intelligence systems can contain a reflection model.
Thus, it is impossible to consider an intellectual system complete without the ability to evaluate and “understand” its actions, that is, to reflect. Moreover, reflection should be considered one of the main tools for constructing the behavior of systems. Speaking in the language of mathematics, reflection is a necessary condition for the existence of an intellectual system.
1.3.4. Knowledge representation languages
In a certain sense, any computer program contains knowledge. A bubble sort program contains the programmer's knowledge of how to order the elements of a list. Understanding the essence of a computer program that solves the problem of sorting lists is not at all easy. It contains the programmer’s knowledge about the method for solving the problem, but, in addition to this knowledge, it also contains others:
− how to manipulate language constructs of the programming language used;
− how to achieve high program performance;
− how to choose appropriate methods for solving particular problems of data processing, which nevertheless play an important role in achieving the final result, and how to organize process management.
Knowledge representation languages are high-level languages specifically designed for explicitly encoding fragments of human knowledge, such as rules of influence and a set of properties of typical objects, and the high level of the language is manifested in the fact that, as far as possible, the technical details of the knowledge representation mechanism are hidden from the user. Unlike more conventional programming languages, knowledge representation languages are extremely economical in terms of the amount of program code. This is largely due to the fact that the language interpreter takes care of many small details.
Despite the noted advantages of such languages, we must not forget about the existence of certain problems in their use.
The transition from describing domain knowledge in all understandable “human” language to its representation in the form of some kind of formalism perceived by a computer requires a certain skill, since it is impossible (at least today) to describe how to mechanically perform such a transformation. Since the logical inference capabilities that a program can implement are directly related to the choice of how to represent knowledge, it is the representation of knowledge, and not its extraction, that is the bottleneck in the practice of ES design.
This tutorial includes the basics of programming in Prolog, solving problems using the search method, probabilistic methods, the basics of neural networks, as well as the principles of knowledge representation using semantic networks. Each section of the textbook is provided with practical and laboratory work. The appendices contain brief descriptions of the SWI-Prolog environment, neural network software
This tutorial covers the basics of programming in Prolog, problem solving using search methods, probabilistic methods, the basics of neural networks, and principles of knowledge representation using semantic networks. Each section of the textbook is provided with practical and laboratory work. The appendices contain brief descriptions of the SWI-Prolog environment, the NeuroGenetic Optimizer neural network modeling program and the Semantic knowledge visualization program. Complies with the current requirements of the Federal State Educational Standard of Higher Education. For students of higher educational institutions studying in engineering and technical fields.
Book " Artificial intelligence systems. Tutorial "The author Bessmertny Igor Aleksandrovich was rated by KnigoGuid visitors, and her reader rating was 0.00 out of 10.
The following are available for free viewing: abstract, publication, reviews, as well as files for downloading.
S.G. TOLMACHEV
ARTIFICIAL INTELLIGENCE.
NEURAL NETWORK MODELS
Ministry of Education and Science Russian Federation Baltic State Technical University "Voenmech"
Department of Information Processing and Management Systems
S.G. TOLMACHEV
ARTIFICIAL INTELLIGENCE.
NEURAL NETWORK MODELS
Tutorial
Saint Petersburg
UDC 004.8(075.8) T52
Tolmachev, S.G.
T52 Artificial intelligence systems. Neural network models: textbook / S.G. Tolmachev; Balt. state tech. univ. – St. Petersburg, 2011. 132 p.
ISBN 978-5 -85546-633-1
Basic information about the structure and principles of operation of artificial neural networks is provided. The functioning of a formal neuron, the classification of neural networks according to their architecture and types of training, typical formulations of various neural network problems and methods for solving them are considered.
Intended for senior students studying in the specialties “Information Systems and Technologies” and “Automated Information Processing and Management Systems”.
UDC 004.8(075.8)
REVIEWERS: Dr. Tech. Sciences prof., head. scientific employee of OJSC "Concern "Granit-Electron"" S.N. Sharov; Ph.D. tech. Sciences, prof., head. department I5 BSTU N.N. Smirnova
Approved by the University's Editorial and Publishing Council
INTRODUCTION
One of the most powerful tools for creating intelligent systems is artificial neural networks (ANN), which model the basic information processing mechanisms inherent in the human brain. It is known that the brain works in a fundamentally different way and often more efficiently than any computing machine created by man. It is this fact that has motivated scientists for many years to work on the creation and research of artificial neural networks.
The brain is an extremely complex information processing system. It has the ability to organize its structural components, called neurons, so that they can perform specific tasks (pattern recognition, sensory processing, motor functions) many times faster than the fastest modern computers. An example of such a task is normal vision. The functions of the visual system include creating an idea of the surrounding world in a form that provides the ability to interact with it. The brain sequentially performs recognition tasks (for example, recognizing a familiar face in an unfamiliar environment) and spends 100...200 ms on this. Completing similar, less complex tasks on a computer can take several hours.
To understand the magnitude of the challenge of creating a machine that performs as perfectly as our brain, we only need to think about some of the routine tasks we perform every day. Let's say you are sitting at your desk, and at this time your colleague, who has returned from vacation, enters the room. He's wearing a new T-shirt, sunglasses on his tanned face, and he looks a little younger because he's shaved his beard. Do you recognize him? Undoubtedly, since disguise is not part of his plans. During the conversation, he asks you: “Where is the book I gave you to read?” You interpret the question as a request to return the book. Then look at your desk and
You see among the books and stacks of papers lying on it the book in question, you reach out to it, take it out of the pile of documents and give it to your colleague. Such everyday tasks do not require much mental effort from us, but solving each of them involves many precisely calculated steps. The difficulty of solving such problems can be felt when trying to program a computer system to recognize objects by their appearance or other characteristics, making decisions depending on the context, etc.
A simpler example is bat sonar, which is an active echo-location system. In addition to providing information about the distance to the desired object, this locator allows you to calculate such object parameters as relative speed, size of individual elements and direction of movement. To extract this information from the received signal, the bat's tiny brain performs complex neural calculations.
What allows the human or bat brain to achieve such results? At birth, the brain already has a perfect structure that allows it to build its own rules based on what is usually called experience. Experience accumulates over time until the last days of a person's life, with particularly large-scale changes occurring in the first two years of life.
The development of neurons is associated with the concept of brain plasticity - the ability to adjust the nervous system in accordance with environmental conditions. Plasticity plays the most important role in the functioning of neurons as elementary information processing units in the human brain. In a similar way, artificial neurons are configured in an ANN. In general, an ANN is a machine that models the way the brain solves a specific problem. This network is implemented using electronic components (neuroprocessors) or modeled by a program running on a digital computer. In order to achieve high performance, ANNs use many connections between elementary computational cells – neurons. Among the many definitions of neural networks, the most accurate is the definition of an ANN as an adaptive machine: artificial neural networkit's distributed
a parallel processor consisting of standard information processing elements that accumulate experimental knowledge and provide it for subsequent processing. A neural network is similar to the brain in two ways:
1) knowledge enters the neural network from the environment
And used by the network in the learning process;
2) To accumulate knowledge, interneuron connections, also called synaptic weights, are used.
The procedure used to carry out the learning process is called a learning algorithm. Its function is to modify the synaptic weights of the ANN in a certain way so that the network acquires the necessary properties.
Modifying weights is a traditional way of training an ANN. This approach is close to the theory of adaptive linear filters that are used in control. However, for an ANN there is also the possibility of modifying its own topology, based on the fact that in a living brain neurons can die off, and new synaptic connections can be created.
Thus, ANNs realize their computing power thanks to their two main properties: a parallel-distributed structure and the ability to learn and generalize acquired knowledge. Generalization property refers to the ability of an ANN to generate correct outputs for input signals that were not taken into account during the learning process. These two properties make ANN an information processing system capable of solving complex multidimensional problems that are currently intractable.
It should be noted that in practice, autonomous ANNs often cannot provide ready-made solutions. They should be integrated into complex systems. A complex problem can be broken down into a number of simpler problems, some of which can be solved by neural networks.
The areas of application of ANN are very diverse: text and speech recognition and analysis, semantic search, expert systems and decision support systems, stock price prediction, security systems. There are several examples of using ANN in different areas.
1. Transport security systems. American company
Science Application International Corporation used ANN in
his TNA project. The device being developed is designed to detect plastic explosives in packed luggage. The luggage is bombarded with particles that cause secondary radiation, the spectrum of which is analyzed by a neural network. The device provides a probability of detecting explosives above 97% and is capable of scanning 10 pieces of luggage per minute.
2. Neural network software packages in financial markets. The American Chemical Bank uses a neural network system from Neural Data to pre-process transactions on currency exchanges, filtering out “suspicious” transactions. Citibank has been using neural network predictions since 1990. Automated dealing shows returns that exceed those of most brokers. It may be noted that the proceedings of the seminar “Artificial Intelligence in Wall Street" comprises several weighty volumes.
3. Monitoring and automatic classification of news. Location
Knowing the subject of text messages is another example of using ANN. The Convectis news server (a product of Aptex Software Inc.) provides automatic classification of messages into categories. By checking the meanings of words by context, Convectis is able to recognize topics in real time and categorize huge flows of text messages transmitted over the networks of Reuters, NBC, CBS, etc. After analyzing the message, an annotation, a list of keywords and a list of categories to which this message belongs are generated
4. Autopiloting of unmanned aerial vehicles. The hypersonic reconnaissance aircraft LoFLYTE (Low-Observable Flight Test Experiment), a 2.5 m long jet unmanned aircraft, was developed for NASA and the US Air Force by Accurate Automation Corp. within the framework of the program to support small innovative businesses. This is an experimental development to explore new principles of piloting. It includes neural networks that allow the autopilot to learn by copying the pilot's flying techniques. Over time, neural networks acquire control experience, and the speed of information processing allows them to quickly find a way out in extreme and emergency situations. LoFLYTE is designed for flight at supersonic speeds, where the pilot's reaction time may not be sufficient to adequately respond to changes in flight conditions.
Nowadays, ANNs are an important extension of the concept of computation. They have already made it possible to cope with a number of difficult problems and promise the creation of new programs and devices capable of solving problems that only humans can currently do. Modern neurocomputers are used primarily as software products and therefore rarely exploit their potential for “parallelism.” The era of real parallel neurocomputations will begin with the appearance on the market of hardware implementations of specialized neurochips and expansion cards designed for processing speech, video, static images and other types of figurative information.
Another area of application of ANNs is their use
V specialized software robotic agents designed to process information rather than perform physical work. Intelligent assistants should make it easier for users to communicate with the computer. Their distinctive feature will be the desire to understand as best as possible what is required of them, through observation and analysis of the behavior of their “master”. Trying to discover
V This behavior has some regularities, intelligent agents must offer their services in a timely manner to perform certain operations, for example, to filter news messages, to backup documents that the user is working on, etc. That is why ANNs, capable of summarizing data and finding patterns in them, are a natural component of such software agents.
1. COMPUTERS AND THE BRAIN
1.1. Biological neuron
The human nervous system can be simplified into a three-stage structure. The center of this system is the brain, consisting of a network of neurons (Fig. 1.1). It receives information, analyzes it and makes appropriate decisions. Receptors convert signals from the environment and internal organs into electrical impulses perceived by the neural network (brain). Receptors provide communication between our brain and the outside world, allowing it to receive visual, auditory, gustatory, olfactory and tactile information. Ef-
Fectors convert electrical impulses generated by the brain into output signals that control muscles, internal organs, and vessel walls. Thus, the brain controls the functioning of the heart, breathing, blood pressure, temperature, maintains the required oxygen content in the blood, etc. Intermediate neurons process information received from sensory neurons and transmit it to effector neurons.
Rice. 1.1. Simplified diagram of the nervous system
It should be noted that the brain is built from two types of cells: glial and neurons. And although the role of glial cells appears to be quite significant, most scientists believe that much of the way to understand how the brain works is by studying neurons connected in a single connected network. This approach is used in the construction of artificial neural networks (ANN).
It should be noted that there are other opinions. Some researchers believe that the main processes occur not in the neural network, but in the cells themselves, namely in their cytoskeleton, in the so-called microtubules. According to this point of view, both memory and even consciousness are determined by changes in proteins in intracellular structures and associated quantum effects.
The number of neurons in the brain is estimated at 1010...1011. In a biological neuron, the following structural units can be distinguished (Fig. 1.2):
cell body (soma);
dendrites are many branching short (no more than 1 mm) nerve fibers that collect information from other neurons;
The axon is the only thin, long (sometimes more than a meter) nerve fiber. The axon ensures the conduction of impulses and transmission of effects to other neurons or muscle fibers. At its termination, the axon also branches and forms contacts with the dendrites of other neurons;
The textbook introduces readers to the history of artificial intelligence, knowledge representation models, expert systems and neural networks. The main directions and methods used in the analysis, development and implementation of intelligent systems are described. Models of knowledge representation and methods of working with them, methods of developing and creating expert systems are considered. The book will help the reader master the skills of logical design of domain databases and programming in the ProLog language.
For students and teachers of pedagogical universities, teachers of secondary schools, gymnasiums, lyceums.
The concept of artificial intelligence.
An artificial intelligence (AI) system is a software system that simulates the human thinking process on a computer. To create such a system, it is necessary to study the very thinking process of a person solving certain problems or making decisions in a specific area, highlight the main steps of this process and develop software that reproduces them on a computer. Therefore, AI methods take a simple structured approach to developing complex software decision-making systems.
Artificial intelligence is a branch of computer science whose goal is to develop hardware and software that allows a non-programmer user to pose and solve their traditionally considered intellectual problems, communicating with a computer in a limited subset of natural language.
TABLE OF CONTENTS
Chapter 1. Artificial Intelligence
1.1. Introduction to Artificial Intelligence Systems
1.1.1. The concept of artificial intelligence
1.1.2. Artificial intelligence in Russia
1.1.3. Functional structure of an artificial intelligence system
1.2. Directions for the development of artificial intelligence
1.3. Data and knowledge. Representation of knowledge in intelligent systems
1.3.1. Data and knowledge. Basic definitions
1.3.2. Knowledge representation models
1.4. Expert systems
1.4.1. Expert system structure
1.4.2. Development and use of expert systems
1.4.3. Classification of expert systems
1.4.4. Representation of knowledge in expert systems
1.4.5. Tools for building expert systems
1.4.6. Expert system development technology
Test questions and assignments for Chapter 1
References for Chapter 1
Chapter 2. Logic programming
2.1. Programming methodologies
2.1.1. Imperative programming methodology
2.1.2. Object-oriented programming methodology
2.1.3. Functional programming methodology
2.1.4. Logic programming methodology
2.1.5. Constraint Programming Methodology
2.1.6. Neural network programming methodology
2.2. A Brief Introduction to Predicate Calculus and Theorem Proving
2.3. Inference Process in Prolog
2.4. Program structure in Prolog language
2.4.1. Using Composite Objects
2.4.2. Using alternative domains
2.5. Organizing repetition in Prolog
2.5.1. Rollback method after failure
2.5.2. Cut and rollback method
2.5.3. Simple recursion
2.5.4. Generalized recursion rule (GRR) method
2.6. Lists in Prolog
2.6.1. Operations on lists
2.7. Strings in Prolog
2.7.1. String Operations
2.8. Files in Prolog
2.8.1. Prolog predicates for working with files
2.8.2. File domain description
2.8.3. Write to file
2.8.4. Reading from a file
2.8.5. Modifying an existing file
2.8.6. Appending to the end of an existing file
2.9. Creating dynamic databases in Prolog
2.9.1. Databases in Prolog
2.9.2. Dynamic Database Predicates in Prolog
2.10. Creation of expert systems
2.10.1. Expert system structure
2.10.2. Knowledge representation
2.10.3. Withdrawal Methods
2.10.4. User Interface System
2.10.5. Rule-based expert system
Test questions and assignments for Chapter 2
References for Chapter 2
Chapter 3. Neural networks
3.1. Introduction to Neural Networks
3.2. Artificial neuron model
3.3. Application of neural networks
3.4. Neural network training
Test questions and assignments for Chapter 3
References for Chapter 3.
Download the e-book for free in a convenient format, watch and read:
Download the book Fundamentals of Artificial Intelligence, Borovskaya E.V., Davydova N.A., 2016 - fileskachat.com, fast and free download.
Tutorial « DBMS: SQL language in examples and problems” by I.F. Astakhova, A.P. Todstobrova, V.M. Melnikova, V.V. Fertikova, published by FIZMATLIT publishing house in 2007 and certified by the Ministry of Education and Science, contains a selection of examples, problems and exercises of varying degrees of complexity to provide practical and laboratory classes to study the basics of the SQL language as part of a training course dedicated to information systems with databases in the field of study and specialty "Applied Mathematics and Computer Science". Information systems using databases currently represent one of the most important areas of modern computer technology. Most of the modern software market is associated with this area. Considering the place occupied by the SQL language in modern information technologies, its knowledge is necessary for any specialist working in this field. Therefore, its practical development is an integral part of training courses aimed at studying information systems with databases. Currently, such courses are included in the curricula of a number of university specialties. There is no doubt that in order to ensure that students have the opportunity to obtain stable skills in the SQL language, the corresponding training course, in addition to theoretical familiarization with the basics of the language, must necessarily contain a sufficiently large amount of laboratory exercises on its practical use. The proposed textbook is aimed primarily at methodological support for just this type of activity. In this regard, it focuses on the selection of practical examples, tasks and exercises of varying degrees of complexity in drawing up SQL queries, allowing for practical language learning sessions to be carried out during the academic semester.
Textbook “Artificial Intelligence Systems. Practical course" by Astakhova I.F., Chulyukova V.A., Potapov A.S., Milovskaya L.S., Kashirina I.L., Bogdanova M.V., Prosvetova Yu.V., which has a UMO stamp according to classical university education and published by BINOM publishing houses. KNOWLEDGE LABORATORY and PHYSMATLIT in 2008, prepared for lectures and laboratory classes in the disciplines “Databanks and expert systems”, “Databases and expert systems”, “Artificial intelligence systems”, “Information intelligent systems”. This book is dedicated to the area of computer science in which last years There is very little domestic educational literature for higher educational institutions. Translated books are more likely to be scientific publications than textbooks. It was necessary to come up with a lot of examples and laboratory tasks that students would perform on a computer and acquire knowledge, skills and abilities (from the point of view of a competency-based approach to education).
The main advantage and significant difference of this textbook from similar publications is the presence in it of about 100 examples, 235 exercises, 79 questions for repeating the material covered, 11 laboratory works in which 6 different software products are studied.
Bibliographic link
Astakhova I.F., Tolstobrov A.P., Chulyukov V.A., Potapov A.S. TEACHING GUIDE “DBMS: SQL LANGUAGE IN EXAMPLES AND TASKS”, “ARTIFICIAL INTELLIGENCE. PRACTICAL COURSE" // Modern problems of science and education. – 2009. – No. 1.;URL: http://science-education.ru/ru/article/view?id=901 (access date: 09/17/2019). We bring to your attention magazines published by the publishing house "Academy of Natural Sciences"
