This document provides information about an Artificial Intelligence course. The key details are:
- The course is CSC 343, taught over 3 lecture hours and 2 lab hours
Cognitive science is the interdisciplinary study of the mind and its processes. It includes psychology, artificial intelligence, neuroscience, linguistics, and other fields. The document provides an overview of the key topics in cognitive science, including knowledge representation, language, learning, thinking, and perception. It also discusses different approaches like symbolic and connectionist computational cognitive science. The goal of cognitive science is to understand how the mind works by studying representations and processes through various methods like computational modeling.
Extending and integrating a hybrid knowledge representation system into the c...Valentina Rho
This document summarizes Valentina Rho's thesis on extending a hybrid knowledge representation system called Dual-PECCS into the cognitive architecture ACT-R. Dual-PECCS represents concepts using both classical and typical information based on dual-process theory. The objectives were (a) extending Dual-PECCS and (b) integrating it into ACT-R. Dual-PECCS was translated into ACT-R chunks and a new action allows accessing its subsystems. Experiments using riddles showed the integrated system had similar accuracy to humans in conceptual categorization and representation proxyfication. Future work includes improving generalization in the typical system and integrating Dual-PECCS into other architectures.
This document provides an overview of artificial intelligence and discusses several key concepts:
1. It defines AI as making computers do things that people do better and discusses the goal of constructing a theory of intelligence.
2. It outlines several early AI problems and techniques like game playing, theorem proving, and expert systems.
3. It discusses challenges like natural language processing, computer vision, and commonsense reasoning that require extensive knowledge to solve.
4. It provides examples of AI techniques like symbolic representation, knowledge bases, and algorithms for solving problems like tic-tac-toe.
This document provides an overview of an introductory course on Artificial Intelligence. It discusses the learning outcomes, which include gaining knowledge of core AI concepts like search, game playing, knowledge representation, planning and machine learning. It emphasizes using Python to construct simple AI systems and developing transferable problem solving skills. The document outlines that students are expected to attend lectures, supplement with textbook reading, and use references. It also gives a high-level overview of the different perspectives and definitions of what constitutes Artificial Intelligence.
This document discusses different definitions and approaches to artificial intelligence (AI). It begins by defining AI as helping machines solve complex problems like humans by applying human-like algorithms. It then discusses AI's links to other fields and its history. The rest of the document explores definitions of AI and different goals or approaches in AI research, including systems that think or act like humans and systems that think or act rationally. It focuses on the Turing Test approach of acting humanly and the cognitive modeling approach of thinking humanly by modeling human cognition.
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062Wael Alawsey
This document provides an overview of artificial intelligence and several AI techniques. It discusses neural networks, genetic algorithms, expert systems, fuzzy logic, and the suitability of AI for solving transportation problems. Neural networks can be used to perform tasks like optical character recognition by analyzing images. Genetic algorithms use principles of natural selection to arrive at optimal solutions. Expert systems mimic human experts to provide advice. Fuzzy logic allows for gradual membership in sets rather than binary membership. Complexity and uncertainty make transportation well-suited for AI approaches.
This document provides an introduction to artificial intelligence (AI). It discusses the history and foundations of AI, including early philosophers who discussed the possibility of machine intelligence. It also defines key AI concepts like intelligence, rational thinking, and acting like humans. The document outlines different types of AI systems and why AI is powerful due to combining knowledge from many disciplines. It concludes with an overview of the history of AI from its beginnings in the 1940s to the growth of expert systems.
Cognitive science is the interdisciplinary study of the mind and its processes. It includes psychology, artificial intelligence, neuroscience, linguistics, and other fields. The document provides an overview of the key topics in cognitive science, including knowledge representation, language, learning, thinking, and perception. It also discusses different approaches like symbolic and connectionist computational cognitive science. The goal of cognitive science is to understand how the mind works by studying representations and processes through various methods like computational modeling.
Extending and integrating a hybrid knowledge representation system into the c...Valentina Rho
This document summarizes Valentina Rho's thesis on extending a hybrid knowledge representation system called Dual-PECCS into the cognitive architecture ACT-R. Dual-PECCS represents concepts using both classical and typical information based on dual-process theory. The objectives were (a) extending Dual-PECCS and (b) integrating it into ACT-R. Dual-PECCS was translated into ACT-R chunks and a new action allows accessing its subsystems. Experiments using riddles showed the integrated system had similar accuracy to humans in conceptual categorization and representation proxyfication. Future work includes improving generalization in the typical system and integrating Dual-PECCS into other architectures.
This document provides an overview of artificial intelligence and discusses several key concepts:
1. It defines AI as making computers do things that people do better and discusses the goal of constructing a theory of intelligence.
2. It outlines several early AI problems and techniques like game playing, theorem proving, and expert systems.
3. It discusses challenges like natural language processing, computer vision, and commonsense reasoning that require extensive knowledge to solve.
4. It provides examples of AI techniques like symbolic representation, knowledge bases, and algorithms for solving problems like tic-tac-toe.
This document provides an overview of an introductory course on Artificial Intelligence. It discusses the learning outcomes, which include gaining knowledge of core AI concepts like search, game playing, knowledge representation, planning and machine learning. It emphasizes using Python to construct simple AI systems and developing transferable problem solving skills. The document outlines that students are expected to attend lectures, supplement with textbook reading, and use references. It also gives a high-level overview of the different perspectives and definitions of what constitutes Artificial Intelligence.
This document discusses different definitions and approaches to artificial intelligence (AI). It begins by defining AI as helping machines solve complex problems like humans by applying human-like algorithms. It then discusses AI's links to other fields and its history. The rest of the document explores definitions of AI and different goals or approaches in AI research, including systems that think or act like humans and systems that think or act rationally. It focuses on the Turing Test approach of acting humanly and the cognitive modeling approach of thinking humanly by modeling human cognition.
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062Wael Alawsey
This document provides an overview of artificial intelligence and several AI techniques. It discusses neural networks, genetic algorithms, expert systems, fuzzy logic, and the suitability of AI for solving transportation problems. Neural networks can be used to perform tasks like optical character recognition by analyzing images. Genetic algorithms use principles of natural selection to arrive at optimal solutions. Expert systems mimic human experts to provide advice. Fuzzy logic allows for gradual membership in sets rather than binary membership. Complexity and uncertainty make transportation well-suited for AI approaches.
This document provides an introduction to artificial intelligence (AI). It discusses the history and foundations of AI, including early philosophers who discussed the possibility of machine intelligence. It also defines key AI concepts like intelligence, rational thinking, and acting like humans. The document outlines different types of AI systems and why AI is powerful due to combining knowledge from many disciplines. It concludes with an overview of the history of AI from its beginnings in the 1940s to the growth of expert systems.
Psychology is a branch of science that studies the behavior, emotion, and thought structure of a living thing. Artificial intelligence, on the other hand, is a system that tries to imitate human behavior, reasoning ability, and problem-solving skills.
Now, with the partnership of these two structures, a new era begins in psychology. Artificial intelligence is ushering in a new era in psychology.
This document provides an overview of artificial intelligence (AI) including definitions of AI, different approaches to AI (strong/weak, applied, cognitive), goals of AI, the history of AI, and comparisons of human and artificial intelligence. Specifically:
1) AI is defined as the science and engineering of making intelligent machines, and involves building systems that think and act rationally.
2) The main approaches to AI are strong/weak, applied, and cognitive AI. Strong AI aims to build human-level intelligence while weak AI focuses on specific tasks.
3) The goals of AI include replicating human intelligence, solving complex problems, and enhancing human-computer interaction.
4) The history of AI
Towards which Intelligence? Cognition as Design Key for building Artificial I...Antonio Lieto
The document discusses approaches to building artificial intelligence systems based on human cognition. It argues that AI should focus on high-level cognitive functions like humans exhibit full intelligence. A cognitive AI approach models heuristics and bounded rationality used by humans. The document presents a case study of a common sense reasoning system that integrates heterogeneous conceptual representations like prototypes and exemplars, and uses a dual process of reasoning. The system is evaluated against human responses in categorization tasks with 84% accuracy, providing insights to refine the cognitive theory.
This document provides an introduction to an artificial intelligence course. The course aims to give students knowledge and understanding of core AI concepts like search, game playing, planning and machine learning. Students will learn how to apply these concepts to construct simple AI systems using a declarative language. The document outlines several core areas of AI including knowledge representation, reasoning, planning, learning, and interacting with the environment. It also discusses the history of AI and provides examples of modern AI applications.
1) Intelligence is defined as the ability to act appropriately in uncertain environments in order to achieve goals and succeed.
2) Natural intelligence evolved through natural selection to produce behaviors that increase survival and reproduction.
3) More intelligent individuals and groups are better able to sense their environment, make decisions, and take actions that provide biological advantages over less intelligent competitors.
The document provides an overview of artificial intelligence including definitions, types of AI tasks, foundations of AI, history of AI, current capabilities and limitations of AI systems, and techniques for problem solving and planning. It discusses machine learning, natural language processing, expert systems, neural networks, search problems, constraint satisfaction problems, linear and non-linear planning approaches. The key objectives of the course are introduced as understanding common AI concepts and having an idea of current and future capabilities of AI systems.
Computational Neuroscience - The Brain - Computer Science InterfaceChristopher Currin
Understanding intelligence is one of the most challenging scientific problems faced by humanity.
This talk will provide an introduction to the multi-disciplinary field of Computational Neuroscience: the questions it seeks to answer and some of the (mathematical & computational) techniques used to investigate how we fundamentally think.
Currently doing his Computational Neuroscience PhD at the University of Cape Town, Chris has a wonderfully weird background in machine learning, neuroscience, and psychology. He is fascinated by how we think and learn, sometimes to a fault, and how this works in both biological and artificial intelligence.
Chris Currin computational neuroscience intro AIMS MIIA 2017-12Christopher Currin
1. Computational neuroscience provides a framework for understanding the brain by building mathematical and computer-based models that encapsulate our emerging understanding of brain functions.
2. We should care because it can help advance research by reducing animal use, understand and cure diseases and disabilities, and advance AI and data science.
3. We can understand the brain using top-down approaches like analyzing how well models predict neural responses and bottom-up approaches like the Blue Brain Project that aims to simulate the brain at the cellular level.
The document provides an overview of artificial intelligence (AI) including its aims, history, and current state. It defines AI as attempting to both understand human thinking and build intelligent entities by systematizing and automating intellectual tasks. The history of AI is discussed from its origins in the 1940s through various periods including its early enthusiasm, a realization of limitations, the rise of knowledge-based systems, AI becoming an industry, and its evolution into a science. Current capabilities are highlighted such as machine planning, chess playing, and medical diagnosis.
Artificial intelligence is the area of computer science focused on creating intelligent machines. The document discusses the history and branches of AI. It provides examples of early successes in games like chess. It also discusses the knowledge needed to learn AI, such as mathematics and programming languages. Finally, it outlines several applications of AI in fields like medicine, transportation, and games.
This document provides an introduction to artificial intelligence (AI) by discussing key concepts related to intelligence and different approaches to defining AI. It examines definitions of intelligence as the ability to reason, understand, learn from experience, and plan complex tasks. AI is defined as attempting to build intelligent computer systems that exhibit human-like intelligence. There are no widely agreed upon definitions of AI, but definitions generally fall into four categories: systems that think like humans, act like humans, think rationally, or act rationally. The document also discusses the Turing test, thinking rationally using logic, knowledge representation, and intelligent agents.
Rahman Ali gave a lecture on artificial intelligence (AI) at Quaid-e-Azam College of Commerce, University of Peshawar. The lecture defined intelligence and AI, discussed the differences between intelligent and conventional computing, and outlined the history and applications of AI. It also reviewed how other fields like philosophy, mathematics, and neuroscience contribute to AI's development.
Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. Specific applications of AI include expert systems, natural language processing, speech recognition, and machine vision. The document discusses what intelligence and artificial intelligence are, provides definitions and examples of artificial intelligence, and explains how artificial intelligence works through machine learning algorithms. It also covers the goals, history, and advantages of artificial intelligence.
This document provides an overview of an artificial intelligence course. The key learning outcomes are knowledge of AI concepts like search, game playing, knowledge representation, planning and machine learning. Students will develop intellectual skills in applying AI principles and practical skills in using Prolog. The course will cover areas of AI like search, vision, planning, machine learning, knowledge representation, logic and expert systems. Students are expected to attend lectures and supplement with textbook reading. The document then provides examples of what AI is, its goals, foundations in fields like philosophy, mathematics and psychology, and main topics like search, knowledge representation, planning and learning.
This document provides an introduction to artificial intelligence (AI) and related concepts. It defines key terms like data, information, knowledge and knowledge base. It discusses different views on defining AI, including thinking humanly, thinking rationally, acting humanly, and acting rationally. The document also covers the history of AI, applications of AI, knowledge representation, and the differences between human and artificial intelligence. It provides examples of expert systems like DENDRAL, MYCIN, PUFF and ELIZA to illustrate the concept.
The Foundations of Artificial Intelligence, The History of
Artificial Intelligence, and the State of the Art. Intelligent Agents: Introduction, How Agents
should Act, Structure of Intelligent Agents, Environments. Solving Problems by Searching:
problem-solving Agents, Formulating problems, Example problems, and searching for Solutions,
Search Strategies, Avoiding Repeated States, and Constraint Satisfaction Search. Informed
Search Methods: Best-First Search, Heuristic Functions, Memory Bounded Search, and Iterative
Improvement Algorithms.
This document discusses artificial intelligence and human intelligence. It defines intelligence as the ability to reason, plan, solve problems, think abstractly, comprehend ideas, use language, and learn. The document then discusses features of intelligence such as adaptability, capacity for knowledge, abstract thought, comprehension of relationships, evaluation, and original thought. It also discusses definitions of artificial intelligence as simulating human intelligence and making computers do things at which people are currently better. The document compares human and artificial intelligence, noting pros and cons of each. Finally, it distinguishes artificial intelligence from conventional computing by describing how AI uses search and pattern matching while conventional software follows logical steps.
Ben Goertzel is the CEO of Novamente LLC and Biomind LLC, and CTO of Genescient Corp. He is also the co-founder of the OpenCog Project and Vice Chairman of Humanity+. OpenCog is an open source software framework and design for advanced artificial general intelligence (AGI). It uses a cognitive architecture based on multiple interacting cognitive processes that act on a shared knowledge representation. Key algorithms in OpenCog include MOSES for probabilistic evolutionary learning, probabilistic logic networks for declarative knowledge, and economic attention allocation for resource management. The goal is to develop AGI with high efficient pragmatic general intelligence relative to relevant goals and environments.
This document discusses the syllabus for the course CS6659 - Artificial Intelligence. It covers 5 units: (1) introduction to AI and production systems, (2) knowledge representation, (3) knowledge inference, (4) planning and machine learning, and (5) expert systems. It also provides definitions of AI, discusses the history and components of AI, and describes the differences between weak AI and strong AI. The document gives an overview of the key concepts and topics that will be covered in the AI course.
Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think.
Artificial intelligence (AI) is an area of computer science that aims to design machines that can think and act intelligently, like humans. The document discusses several key aspects of AI including:
- The goals of AI such as learning, reasoning, understanding language.
- Examples of modern AI applications like defeating chess champions, driving vehicles autonomously, and assisting with medical diagnoses.
- The history and development of AI from its origins in the 1950s to modern areas like neural networks.
- Challenges in developing truly intelligent machines that can match all aspects of human intelligence like creativity and common sense.
Psychology is a branch of science that studies the behavior, emotion, and thought structure of a living thing. Artificial intelligence, on the other hand, is a system that tries to imitate human behavior, reasoning ability, and problem-solving skills.
Now, with the partnership of these two structures, a new era begins in psychology. Artificial intelligence is ushering in a new era in psychology.
This document provides an overview of artificial intelligence (AI) including definitions of AI, different approaches to AI (strong/weak, applied, cognitive), goals of AI, the history of AI, and comparisons of human and artificial intelligence. Specifically:
1) AI is defined as the science and engineering of making intelligent machines, and involves building systems that think and act rationally.
2) The main approaches to AI are strong/weak, applied, and cognitive AI. Strong AI aims to build human-level intelligence while weak AI focuses on specific tasks.
3) The goals of AI include replicating human intelligence, solving complex problems, and enhancing human-computer interaction.
4) The history of AI
Towards which Intelligence? Cognition as Design Key for building Artificial I...Antonio Lieto
The document discusses approaches to building artificial intelligence systems based on human cognition. It argues that AI should focus on high-level cognitive functions like humans exhibit full intelligence. A cognitive AI approach models heuristics and bounded rationality used by humans. The document presents a case study of a common sense reasoning system that integrates heterogeneous conceptual representations like prototypes and exemplars, and uses a dual process of reasoning. The system is evaluated against human responses in categorization tasks with 84% accuracy, providing insights to refine the cognitive theory.
This document provides an introduction to an artificial intelligence course. The course aims to give students knowledge and understanding of core AI concepts like search, game playing, planning and machine learning. Students will learn how to apply these concepts to construct simple AI systems using a declarative language. The document outlines several core areas of AI including knowledge representation, reasoning, planning, learning, and interacting with the environment. It also discusses the history of AI and provides examples of modern AI applications.
1) Intelligence is defined as the ability to act appropriately in uncertain environments in order to achieve goals and succeed.
2) Natural intelligence evolved through natural selection to produce behaviors that increase survival and reproduction.
3) More intelligent individuals and groups are better able to sense their environment, make decisions, and take actions that provide biological advantages over less intelligent competitors.
The document provides an overview of artificial intelligence including definitions, types of AI tasks, foundations of AI, history of AI, current capabilities and limitations of AI systems, and techniques for problem solving and planning. It discusses machine learning, natural language processing, expert systems, neural networks, search problems, constraint satisfaction problems, linear and non-linear planning approaches. The key objectives of the course are introduced as understanding common AI concepts and having an idea of current and future capabilities of AI systems.
Computational Neuroscience - The Brain - Computer Science InterfaceChristopher Currin
Understanding intelligence is one of the most challenging scientific problems faced by humanity.
This talk will provide an introduction to the multi-disciplinary field of Computational Neuroscience: the questions it seeks to answer and some of the (mathematical & computational) techniques used to investigate how we fundamentally think.
Currently doing his Computational Neuroscience PhD at the University of Cape Town, Chris has a wonderfully weird background in machine learning, neuroscience, and psychology. He is fascinated by how we think and learn, sometimes to a fault, and how this works in both biological and artificial intelligence.
Chris Currin computational neuroscience intro AIMS MIIA 2017-12Christopher Currin
1. Computational neuroscience provides a framework for understanding the brain by building mathematical and computer-based models that encapsulate our emerging understanding of brain functions.
2. We should care because it can help advance research by reducing animal use, understand and cure diseases and disabilities, and advance AI and data science.
3. We can understand the brain using top-down approaches like analyzing how well models predict neural responses and bottom-up approaches like the Blue Brain Project that aims to simulate the brain at the cellular level.
The document provides an overview of artificial intelligence (AI) including its aims, history, and current state. It defines AI as attempting to both understand human thinking and build intelligent entities by systematizing and automating intellectual tasks. The history of AI is discussed from its origins in the 1940s through various periods including its early enthusiasm, a realization of limitations, the rise of knowledge-based systems, AI becoming an industry, and its evolution into a science. Current capabilities are highlighted such as machine planning, chess playing, and medical diagnosis.
Artificial intelligence is the area of computer science focused on creating intelligent machines. The document discusses the history and branches of AI. It provides examples of early successes in games like chess. It also discusses the knowledge needed to learn AI, such as mathematics and programming languages. Finally, it outlines several applications of AI in fields like medicine, transportation, and games.
This document provides an introduction to artificial intelligence (AI) by discussing key concepts related to intelligence and different approaches to defining AI. It examines definitions of intelligence as the ability to reason, understand, learn from experience, and plan complex tasks. AI is defined as attempting to build intelligent computer systems that exhibit human-like intelligence. There are no widely agreed upon definitions of AI, but definitions generally fall into four categories: systems that think like humans, act like humans, think rationally, or act rationally. The document also discusses the Turing test, thinking rationally using logic, knowledge representation, and intelligent agents.
Rahman Ali gave a lecture on artificial intelligence (AI) at Quaid-e-Azam College of Commerce, University of Peshawar. The lecture defined intelligence and AI, discussed the differences between intelligent and conventional computing, and outlined the history and applications of AI. It also reviewed how other fields like philosophy, mathematics, and neuroscience contribute to AI's development.
Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. Specific applications of AI include expert systems, natural language processing, speech recognition, and machine vision. The document discusses what intelligence and artificial intelligence are, provides definitions and examples of artificial intelligence, and explains how artificial intelligence works through machine learning algorithms. It also covers the goals, history, and advantages of artificial intelligence.
This document provides an overview of an artificial intelligence course. The key learning outcomes are knowledge of AI concepts like search, game playing, knowledge representation, planning and machine learning. Students will develop intellectual skills in applying AI principles and practical skills in using Prolog. The course will cover areas of AI like search, vision, planning, machine learning, knowledge representation, logic and expert systems. Students are expected to attend lectures and supplement with textbook reading. The document then provides examples of what AI is, its goals, foundations in fields like philosophy, mathematics and psychology, and main topics like search, knowledge representation, planning and learning.
This document provides an introduction to artificial intelligence (AI) and related concepts. It defines key terms like data, information, knowledge and knowledge base. It discusses different views on defining AI, including thinking humanly, thinking rationally, acting humanly, and acting rationally. The document also covers the history of AI, applications of AI, knowledge representation, and the differences between human and artificial intelligence. It provides examples of expert systems like DENDRAL, MYCIN, PUFF and ELIZA to illustrate the concept.
The Foundations of Artificial Intelligence, The History of
Artificial Intelligence, and the State of the Art. Intelligent Agents: Introduction, How Agents
should Act, Structure of Intelligent Agents, Environments. Solving Problems by Searching:
problem-solving Agents, Formulating problems, Example problems, and searching for Solutions,
Search Strategies, Avoiding Repeated States, and Constraint Satisfaction Search. Informed
Search Methods: Best-First Search, Heuristic Functions, Memory Bounded Search, and Iterative
Improvement Algorithms.
This document discusses artificial intelligence and human intelligence. It defines intelligence as the ability to reason, plan, solve problems, think abstractly, comprehend ideas, use language, and learn. The document then discusses features of intelligence such as adaptability, capacity for knowledge, abstract thought, comprehension of relationships, evaluation, and original thought. It also discusses definitions of artificial intelligence as simulating human intelligence and making computers do things at which people are currently better. The document compares human and artificial intelligence, noting pros and cons of each. Finally, it distinguishes artificial intelligence from conventional computing by describing how AI uses search and pattern matching while conventional software follows logical steps.
Ben Goertzel is the CEO of Novamente LLC and Biomind LLC, and CTO of Genescient Corp. He is also the co-founder of the OpenCog Project and Vice Chairman of Humanity+. OpenCog is an open source software framework and design for advanced artificial general intelligence (AGI). It uses a cognitive architecture based on multiple interacting cognitive processes that act on a shared knowledge representation. Key algorithms in OpenCog include MOSES for probabilistic evolutionary learning, probabilistic logic networks for declarative knowledge, and economic attention allocation for resource management. The goal is to develop AGI with high efficient pragmatic general intelligence relative to relevant goals and environments.
This document discusses the syllabus for the course CS6659 - Artificial Intelligence. It covers 5 units: (1) introduction to AI and production systems, (2) knowledge representation, (3) knowledge inference, (4) planning and machine learning, and (5) expert systems. It also provides definitions of AI, discusses the history and components of AI, and describes the differences between weak AI and strong AI. The document gives an overview of the key concepts and topics that will be covered in the AI course.
Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think.
Artificial intelligence (AI) is an area of computer science that aims to design machines that can think and act intelligently, like humans. The document discusses several key aspects of AI including:
- The goals of AI such as learning, reasoning, understanding language.
- Examples of modern AI applications like defeating chess champions, driving vehicles autonomously, and assisting with medical diagnoses.
- The history and development of AI from its origins in the 1950s to modern areas like neural networks.
- Challenges in developing truly intelligent machines that can match all aspects of human intelligence like creativity and common sense.
This document provides an introduction to artificial intelligence and cognitive science. It defines intelligence and AI, discusses different approaches to AI like thinking like humans, thinking rationally, acting like humans and acting rationally. It also summarizes the history of AI from early neural networks to modern applications. Key concepts covered include the Turing test, knowledge representation, rational agents, intelligent environments and knowledge-based systems.
This document provides an overview of artificial intelligence including:
- It defines four approaches to AI: acting humanly through the Turing test, thinking humanly through cognitive modeling, thinking rationally through symbolic logic, and acting rationally as intelligent agents.
- It then summarizes the history of AI from its origins in the 1940s through developments in knowledge-based systems, connectionism, and the emergence of intelligent agents using large datasets.
- Finally, it briefly discusses recent applications of AI such as algorithms used by Facebook, TikTok, and noise cancellation in Zoom calls.
This document provides lecture notes on soft computing techniques. It covers four modules:
1) Introduction to neurofuzzy and soft computing, including fuzzy sets, fuzzy rules, fuzzy inference systems
2) Neural networks, including single layer networks, multilayer perceptrons, unsupervised learning networks
3) Genetic algorithms and derivative-free optimization
4) Evolutionary computing techniques like simulated annealing and swarm optimization.
The document discusses key concepts in soft computing like fuzzy logic, neural networks, evolutionary algorithms and their applications in areas like control systems and pattern recognition. It also provides references for further reading.
This document provides an overview of artificial intelligence techniques. It begins with definitions of AI and discusses branches of AI like logical AI, search, pattern recognition, knowledge representation, inference and more. It also discusses AI applications, problems in AI and the levels of modeling human intelligence. Several examples are then provided to illustrate increasingly sophisticated AI techniques for playing tic-tac-toe and answering questions to demonstrate moving towards knowledge representations that generalize information and are more extensible.
The document discusses artificial intelligence and how it works. It defines intelligence and AI, explaining that AI aims to make computers as intelligent as humans. It describes how AI uses artificial neurons and networks to function similarly to the human brain. Examples of AI applications are given, like expert systems used in various domains. The document also compares human and artificial intelligence, noting their differing strengths and weaknesses.
EELU AI lecture 1- fall 2022-2023 - Chapter 01- Introduction.pptDaliaMagdy12
This document provides an overview of the ITF308-Artificial Intelligence course for 2022-2023. The course will cover foundations of symbolic intelligent systems including agents, search, problem solving, learning, knowledge representation, and reasoning. Programming experience in C++ or Java is required. The textbook is Artificial Intelligence: A Modern Approach by Russell and Norvig. Grading will be based on assignments, attendance, quizzes, a midterm, and a final exam. The course aims to understand intelligent behavior and build intelligent agents/systems through topics like search algorithms, knowledge representation, learning, and reasoning.
Describe what is Artificial Intelligence. What are its goals and Approaches. Different Types of Artificial Intelligence Explain Machine learning and took one Algorithm "K-means Algorithm" and explained
The document discusses several topics related to artificial intelligence including definitions of intelligence and AI, approaches to AI like symbolic AI and biological AI, applications of AI such as expert systems and game playing, and techniques like the Turing test. It also provides a brief history of AI from 1943 to the present day and discusses components of AI programs like knowledge bases, control strategies, and inference mechanisms.
The document discusses artificial intelligence and how it works. It defines artificial intelligence as making computers do intelligent tasks like humans. It discusses neural networks which are composed of artificial neurons that mimic biological neurons. The document also discusses machine learning approaches like failure driven learning, learning by being told, and learning by exploration. Examples of applications of AI are given, like expert systems used in geology and medicine. The key differences between human and artificial intelligence are noted.
The document provides an overview of artificial intelligence (AI) including definitions, techniques, and challenges. It discusses how AI aims to make computers intelligent like humans by giving them abilities such as perception, reasoning, learning, and problem solving. Some key techniques mentioned are search, knowledge representation, and abstraction. The document also discusses the Turing Test as a proposed method for determining if a machine can think like a human. It provides examples of problems AI aims to solve such as game playing, commonsense reasoning, and perception.
This document discusses artificial intelligence (AI) and related concepts. It defines AI as making computers do things that require human intelligence. It explains that AI works using artificial neurons in neural networks and scientific theorems. Neural networks are composed of interconnected artificial neurons that mimic biological neurons. The document also discusses machine learning methods, expert systems, applications of expert systems, the Turing test, and comparisons between human and artificial intelligence.
This document provides an overview of artificial intelligence (AI). It defines intelligence and AI, explaining that AI aims to make computers intelligent like humans. It describes how AI works using artificial neurons and logic. Neural networks are composed of interconnected artificial neurons that mimic biological neurons. The document also discusses applications of expert systems and machine learning. It compares human and artificial intelligence, noting strengths of each. In the end, it argues that AI is humanity's attempt to build models of ourselves and should not be feared.
Artificial intelligence (AI) is defined as making computers do intelligent tasks like humans. It works using artificial neurons in neural networks and scientific theorems. Neural networks are composed of interconnected artificial neurons that mimic biological neurons. The Turing test tests a machine's ability to demonstrate intelligence through conversation. Machine learning allows AI to learn in three ways: from failures, being told, and exploration. Expert systems apply human expertise to problem solving. While AI can process large data quickly, it lacks common sense, intuition, and critical thinking that humans have. Overall, AI is an attempt to build models of human intelligence.
Artificial intelligence aims to replicate human intelligence by enabling computers and machines to perform tasks typically requiring human intelligence like decision making, problem solving, and learning. Early pioneers in the field developed the concepts in the 1940s-1950s, and the field has since made progress in areas like expert systems, machine learning, and natural language processing. While AI has many potential benefits, fully replicating general human intelligence with machines remains a challenge due to our limited understanding of cognition, learning, and other human attributes like creativity.
This document provides an introduction to artificial intelligence, including definitions, foundations, history, and techniques. It defines AI as attempting to understand and build intelligent devices by covering activities like perception, reasoning, and knowledge representation. The key foundations of AI are discussed, such as acting humanly through the Turing test versus acting rationally. The origins and development of AI from the 1940s to today are outlined, highlighting influential researchers and milestones. Advanced techniques discussed include game playing, autonomous control, diagnosis, planning, and language understanding.
This document provides an introduction to artificial intelligence, including definitions, foundations, history, and techniques. It defines AI as attempting to understand and build intelligent devices by replicating tasks like perception, reasoning, and knowledge representation. The key foundations are acting humanly through tests like the Turing Test versus acting rationally by building intelligent agents. The history outlines early work in the 1940s-50s and origins of the field in 1956, followed by growth of expert systems, neural networks, and current techniques like autonomous planning, game playing, diagnosis, and robotics.
This document provides an overview of artificial intelligence (AI). It defines AI as the science of developing methods to solve problems usually associated with human intelligence. The document discusses different definitions and visions of AI, including thinking and acting like humans, thinking and acting rationally, and modeling human thinking through computational models. It also covers the history of AI from its origins in the 1940s to recent successes, as well as related fields and main areas of AI research like machine learning, robotics, and natural language processing.
Similar to Artificial intelligent Lec 1-ai-introduction- (20)
The document discusses the development of cognitive systems and artificial intelligence. It provides an overview of IBM's Watson, a question answering computer system capable of answering questions posed in natural language. The document describes Watson's architecture which involves question analysis, hypothesis generation, evidence scoring, and synthesis to arrive at answers. It details how Watson was able to compete successfully on the game show Jeopardy and is now being developed to assist with medical applications.
This document discusses the future of artificial cognitive systems. It outlines several key topics including the main cognitive processes, the role of tacit knowledge in cognition, progress made in building cognitive systems, and potential architectures for cognitive systems. The document also discusses using spike neural networks for perception in cognitive systems and research into artificial consciousness systems. It provides examples of organizations researching cognitive computing and predicts continued advances that will require collaboration across academia, government and industry.
The document provides an overview of knowledge representation and logic. It discusses knowledge-based agents and how they use a knowledge base to represent facts about the world through sentences expressed in a knowledge representation language. It then covers different knowledge representation schemas including propositional logic, first-order logic, rules, networks, and structures. The document also discusses inference, different types of logic, and knowledge representation languages.
The document discusses various concepts related to state-space search problems and algorithms. It begins by introducing state-space representation and search trees, then describes concepts like search paths, costs, and strategies. It contrasts uninformed searches like breadth-first search which expand nodes by depth, with informed searches like A* that use heuristics. Breadth-first search is discussed in more detail, including that it expands the shallowest nodes first and adds generated states to the back of the queue.
1) Intelligent agents are systems that perceive their environment and act upon it. They can be designed to act or think rationally or humanly.
2) An agent is anything that can perceive its environment through sensors and act upon the environment through effectors. Agents perceive the environment via sensors and act with effectors, mapping percept sequences to actions.
3) Key properties of intelligent agents include autonomy, reactivity, proactiveness, balancing reactive and goal-oriented behavior, and social ability. Agents must be able to operate independently, respond to changes, pursue goals, and interact with other agents.
The document discusses image enhancement techniques in the frequency domain. It introduces Fourier transforms and how they can be used to represent images as a combination of different frequencies. Lowpass and highpass filtering techniques are described for smoothing or sharpening images by modifying specific frequency components. Filters like ideal, Butterworth, and Gaussian are covered. The summary applies filtering in the frequency domain to enhance images.
This document provides information about an image processing course. The key details are:
- The course number is CSC 447 and is taught over 3 lecture hours and 2 lab hours. It is worth 65 marks and has a 3 hour exam.
- The course covers topics like image processing applications, enhancement techniques, restoration, segmentation, and scene analysis. It also covers specific techniques like using neural networks and parallel algorithms for image processing.
- The textbook for the course is "Digital Image Processing Using Matlab" by Rafael Gonzalez and Richard Woods. There are 11 lab assignments focused on topics like image display, filtering, transforms, and color conversion using Matlab.
- The course is taught by
Verification and validation are processes to ensure a software system meets user needs. Verification checks that the product is being built correctly, while validation checks it is the right product. Both are life-cycle processes applying at each development stage. The goal is to discover defects and assess usability. Testing can be static like code analysis or dynamic by executing the product. Different testing types include unit, integration, system, and acceptance testing. An effective testing process involves planning test cases, executing them, and evaluating results.
1. The document discusses software design principles for the waterfall software process.
2. It outlines 11 design principles including dividing problems into smaller components, increasing cohesion, reducing coupling, keeping abstraction high, and designing for flexibility, reusability, portability, and defensiveness.
3. It also discusses design techniques like using priorities and objectives to evaluate alternatives and make design decisions.
The document discusses Unified Modeling Language (UML) diagrams, including state diagrams, sequence diagrams, and collaboration diagrams. It provides details on how to construct and interpret each type of diagram. State diagrams depict object states and transitions between states. Sequence diagrams show the messages passed between objects over time. Collaboration diagrams emphasize object relationships and indicate message sequences with numbers. Both sequence and collaboration diagrams can model the same interactions between objects.
This document discusses object-oriented concepts in software development. It describes the four main types of object-oriented paradigms used in the software lifecycle: object-oriented analysis, design, programming, and testing. It then explains some benefits of the object-oriented approach like modularity, reusability, and mapping to real-world entities. Key concepts like inheritance, encapsulation, and polymorphism are defined. The document also provides examples of how classes and objects are represented and compares procedural with object-oriented programming.
Requirements engineering involves analyzing user needs and constraints to define the services and limitations of a software system. It has several key steps:
1. Requirements analysis identifies stakeholders and understands requirements through client interviews to define both functional requirements about system services and non-functional constraints.
2. Requirements are documented in a requirements specification that defines what the system should do without describing how.
3. The document is validated through reviews and prototyping to ensure requirements accurately capture user needs before development begins.
The document discusses software project management. It states that project management is needed to ensure software is delivered on time, on budget, and according to requirements, as software development is constrained by schedules and budgets set by developing organizations. It describes key project management activities like establishing objectives and plans, assigning resources, tracking costs and progress, and recommending corrective actions. It also discusses challenges like inadequate resources, unrealistic deadlines, unclear goals, and communication breakdowns that can cause projects to fail if not properly managed.
The document discusses software engineering processes used by Microsoft and others. It describes the basic steps in software development as requirements, design, implementation, testing, and maintenance. Two common process models are described: the sequential waterfall model and iterative spiral model. The waterfall model has disadvantages because later stages often require revisions to earlier stages. Most modified versions of the waterfall model allow some iteration and feedback between stages. The spiral model iterates through requirements, design, implementation, and evaluation in cycles to refine the software. The document also briefly discusses other lifecycle models such as incremental development and extreme programming.
This document provides an overview of a software engineering course. The course objectives are to understand how to build complex software systems while dealing with change, produce high-quality software on time, and acquire both technical and managerial knowledge. The main topics covered include the software process, project management, system models, requirements analysis, design principles, verification and validation, testing techniques, and quality assurance. Recommended textbooks are also listed.
The document provides guidance on improving speech and writing styles, different types of letters, and cover letter formatting. It discusses writing formal versus informal letters and describes the standard paragraphs in a letter. Key elements of cover letters are outlined such as addressing the recipient, introductory and concluding paragraphs, highlighting relevant qualifications, and active versus vague language. Tips are given for effective writing, common phrases, and elements to avoid in cover letters. Sample cover letters and information on CVs/resumes and thank you letters are also included.
This document provides guidance on writing in plain language and proper document formatting. It discusses using shorter words and sentences, everyday language, and placing words carefully for clarity. Abbreviations, acronyms, punctuation and paragraph structure are also outlined. The goal is to make information easy to understand by matching the reading level of the intended audience.
This document provides guidance on formatting and structuring technical reports. It recommends numbering sections and paragraphs to make it easy for readers to provide feedback. It also emphasizes including figures, tables, equations and appendices to effectively communicate information, and using consistent formatting of headings, fonts, and styles. Finally, it advises going through multiple revisions to improve accuracy, clarity, organization, conciseness, and correct errors before finalizing the report.
The document provides guidance on writing technical reports, outlining 10 key laws for technical report writing. It discusses important sections of a technical report such as the introduction, methodology, results, discussion, conclusions, and references. It emphasizes that the reader is the most important consideration and that reports must be well-organized, accurate, and concise. Technical reports should follow standard structures and include necessary sections like the executive summary, introduction, methodology, results, discussion, and conclusions.
How to Setup Warehouse & Location in Odoo 17 InventoryCeline George
In this slide, we'll explore how to set up warehouses and locations in Odoo 17 Inventory. This will help us manage our stock effectively, track inventory levels, and streamline warehouse operations.
How to Manage Your Lost Opportunities in Odoo 17 CRMCeline George
Odoo 17 CRM allows us to track why we lose sales opportunities with "Lost Reasons." This helps analyze our sales process and identify areas for improvement. Here's how to configure lost reasons in Odoo 17 CRM
This presentation includes basic of PCOS their pathology and treatment and also Ayurveda correlation of PCOS and Ayurvedic line of treatment mentioned in classics.
हिंदी वर्णमाला पीपीटी, hindi alphabet PPT presentation, hindi varnamala PPT, Hindi Varnamala pdf, हिंदी स्वर, हिंदी व्यंजन, sikhiye hindi varnmala, dr. mulla adam ali, hindi language and literature, hindi alphabet with drawing, hindi alphabet pdf, hindi varnamala for childrens, hindi language, hindi varnamala practice for kids, https://www.drmullaadamali.com
Exploiting Artificial Intelligence for Empowering Researchers and Faculty, In...Dr. Vinod Kumar Kanvaria
Exploiting Artificial Intelligence for Empowering Researchers and Faculty,
International FDP on Fundamentals of Research in Social Sciences
at Integral University, Lucknow, 06.06.2024
By Dr. Vinod Kumar Kanvaria
This presentation was provided by Steph Pollock of The American Psychological Association’s Journals Program, and Damita Snow, of The American Society of Civil Engineers (ASCE), for the initial session of NISO's 2024 Training Series "DEIA in the Scholarly Landscape." Session One: 'Setting Expectations: a DEIA Primer,' was held June 6, 2024.
Strategies for Effective Upskilling is a presentation by Chinwendu Peace in a Your Skill Boost Masterclass organisation by the Excellence Foundation for South Sudan on 08th and 09th June 2024 from 1 PM to 3 PM on each day.
বাংলাদেশের অর্থনৈতিক সমীক্ষা ২০২৪ [Bangladesh Economic Review 2024 Bangla.pdf] কম্পিউটার , ট্যাব ও স্মার্ট ফোন ভার্সন সহ সম্পূর্ণ বাংলা ই-বুক বা pdf বই " সুচিপত্র ...বুকমার্ক মেনু 🔖 ও হাইপার লিংক মেনু 📝👆 যুক্ত ..
আমাদের সবার জন্য খুব খুব গুরুত্বপূর্ণ একটি বই ..বিসিএস, ব্যাংক, ইউনিভার্সিটি ভর্তি ও যে কোন প্রতিযোগিতা মূলক পরীক্ষার জন্য এর খুব ইম্পরট্যান্ট একটি বিষয় ...তাছাড়া বাংলাদেশের সাম্প্রতিক যে কোন ডাটা বা তথ্য এই বইতে পাবেন ...
তাই একজন নাগরিক হিসাবে এই তথ্য গুলো আপনার জানা প্রয়োজন ...।
বিসিএস ও ব্যাংক এর লিখিত পরীক্ষা ...+এছাড়া মাধ্যমিক ও উচ্চমাধ্যমিকের স্টুডেন্টদের জন্য অনেক কাজে আসবে ...
How to Make a Field Mandatory in Odoo 17Celine George
In Odoo, making a field required can be done through both Python code and XML views. When you set the required attribute to True in Python code, it makes the field required across all views where it's used. Conversely, when you set the required attribute in XML views, it makes the field required only in the context of that particular view.
How to Build a Module in Odoo 17 Using the Scaffold MethodCeline George
Odoo provides an option for creating a module by using a single line command. By using this command the user can make a whole structure of a module. It is very easy for a beginner to make a module. There is no need to make each file manually. This slide will show how to create a module using the scaffold method.
A workshop hosted by the South African Journal of Science aimed at postgraduate students and early career researchers with little or no experience in writing and publishing journal articles.
South African Journal of Science: Writing with integrity workshop (2024)
Artificial intelligent Lec 1-ai-introduction-
1.
2. Artificial Intelligence
Course No.: CSC 343
Lect.: 3 h
Lab. : 2 h
Marks: 65 final
10 Y. work
25 Lab+ Oral
Exam hours: 3 h
By Prof. Dr. :
Taymoor M. Nazmy
3. The text book
Russell & Norvig,
"Artificial Intelligence:
A Modern Approach",
2nd Edition, Prentice Hall,
2003.
4. Course Objective
A broad introduction and appreciation of Artificial
Intelligence and its applications.
Course Outline
Definition of Artificial Intelligence. Modelling
intelligence: adaptive and knowledge based
approaches to analysis and design of intelligent
systems. Application domains of Artificial
Intelligence. Types of Artificial Intelligence systems.
5. Course Content
Introduction
Rational Agents
Search and Problem
solving
Informed search
Propositional logic
Predicate logic
Knowledge representation
using logic
Planning
Probabilistic Reasoning
Planning under
uncertainty
Machine Learning
Reinforcement learning
Neural Networks
Natural Language
Processing
6.
7. What is Artificial
Intelligence?
definitions
Turing test
rational thinking
acting rationally
Foundations of Artificial
Intelligence
philosophy
mathematics
psychology
computer science
linguistics
History of Artificial
Intelligence
Applications of AI
8. -select a task that you believe requires intelligence
examples:
-playing chess, solving puzzles, translating from English to
German, finding a proof for a theorem.
-for that task, sketch a computer-based system that tries to
solve the task architecture, components, behavior.
what are the computational methods your system relies on-
e.g. data bases, matrix multiplication, graph traversal.
what are the main challenges?
how do humans tackle the task?
10. Foundations of AI
Engineering:
robotics, vision, control-expert systems, biometrics,
Computer Science:
AI-languages , knowledge representation, algorithms, …
Pure Sciences:
statistics approaches, neural nets, fuzzy logic, …
Linguistics:
computational linguistics, phonetics , speech, …
Psychology:
cognitive models, knowledge-extraction from experts, …
Medicine:
human neural models, neuroscience,...
11. Fundamental Issues for most AI problems
1- Representation
Facts about the world have to be represented in some
way, e.g., mathematical logic is one language that is
used in AI.
Deals with the questions of what to represent and how
to represent it. How to structure knowledge? What is
explicit, and what must be inferred? How to encode
"rules" for inferencing so as to find information that is
only implicitly known?
How to deal with incomplete, inconsistent, and
probabilistic knowledge?
12. 2-Search
Many tasks can be viewed as searching a very large
problem space for a solution. For example, Checkers
has about 1040 states, and Chess has about 10120
states in a typical games. Use of heuristics (meaning
"serving to aid discovery") and constraints.
3-Inference
From some facts others can be inferred. Related to
search. For example, knowing "All elephants have
trunks" and "Clyde is an elephant," can we answer
the question "Does Clyde have a trunk?"
Deduction, abduction, reasoning under uncertainty.
13. 4-Learning
Inductive inference, neural networks, genetic algorithms,
evolutionary approaches.
5-Planning
Starting with general facts about the world, facts about
the effects of basic actions, facts about a particular
situation, and a statement of a goal, generate a strategy
for achieving that goals in terms of a sequence of
primitive steps or actions.
14. “AI develops programming paradigms, languages,
tools, and environments for application areas for which
conventional programming fails”, such as:
Symbolic programming (LISP)
Logical Programming (PROLOG)
Rule-based Programming (Expert system shells)
Soft Computing (Belief network tools, fuzzy logic
tool boxes,…)
Object-oriented programming (Smalltalk)
16. What is AI?
Many definitions, most fit into one of four categories:
Systems that act humanly
Systems that think humanly
Systems that act rationally
Systems that think rationally
17. Systems that think like humans
Cognitive science
Fascinating area, but we will not be covering it in
this course.
Systems that think rationally
Aristotle: What are the correct thought processes
Systems that reason in a logical manner
Systems doing inference correctly.
Systems that act rationally
(Rational behavior ) Doing the right thing
Rational agent approach
Agent: entity that perceives and acts
Rational agent: acts so to achieve best outcome
18. Turing in 1950 published a philosophical paper designed to
stop people arguing about whether or not machines could
think. He proposed that the question be replaced with a test.
19. Acting Rationally
Acting rationally means that one acts to achieve
his/her goals given his/her beliefs.
AI can be viewed as the study and creation of rational
agents. An agent is something that can perceive
and act.
The study of AI as rational agent design has two
advantages:
(a) it is more general than the “laws of thought”
approach, and
(b) it is more amenable to scientific development
than approaches that limit themselves to human
behavior or human thought.
25. Examples of Modeling Human Intelligence
Semantic networks are designed after the
psychological model of the human
associative memory.
John Plumber Person
Owner Ford Car
May 97 Time
Oct 00
Ownership Situation
Is a Is a
Is a
Is a
Is a
Is a
Owner
Ownee
Start-time
End-time
Ford
Is a
26. Modeling Human Intelligence
Rule-based or Expert systems - Knowledge bases
consisting of hundreds or thousands of rules of the form:
IF (condition) THEN (action).
Use rules to store knowledge (“rule-based”).
The rules are usually gathered from experts in the field
being represented (“expert system”).
Most widely used knowledge model in the commercial world.
IF (it is raining AND you must go outside)
THEN (put on your raincoat)
Rules can fire off a chain of other rules
IF (raincoat is on)
THEN (will not get wet)
27. Expert Systems
Expert systems were commercially the most
successful domain in Artificial Intelligence.
Somewhat out of favor today
These programs mimic the experts in whatever
field.
Auto mechanic Telephone networking
Cardiologist Delivery routing
Organic compounds Professional auditor
Mineral prospecting Manufacturing
Infectious diseases Pulmonary function
Diagnostic internal medicine Weather forecasting
VAX computer configuration Battlefield tactician
Engineering structural analysis Space-station life support
Audiologist Civil law
28. Expert Systems
Two major parts of an expert system:
The knowledge base: The collection of rules
that make up the expert system.
The inference engine: A program that uses the
rules by making several passes over them.
On each pass, the inference engine looks for all
rules whose condition is satisfied (if part).
It then takes the action (then part) and makes
another pass over all the rules looking for matching
condition.
This goes on until no rules’ conditions are matched.
The results are all those action parts left.
29. Human Brain and Neural Networks
-Human Brain is made up of Billions of cells called
neurons,
- Neurons work when grouped together Decisions
are made by passing electrical signals,
- Neurons are devices for processing Binary digits,
-A neuron: many-inputs / one-output unit,
-output can be excited or not excited,
-incoming signals from other neurons determine if
the neuron shall excite ("fire")
Output subject to attenuation in the synapses, which
are junction parts of the neuron
30. Artificial Neural Network: A collection of neurons
which are interconnected. The output of one connects to
several others with different strength connections.
Initially, neural networks have no knowledge. (All
information is learned from experience using the
network.)
Input 1
Input 2
Input 3
Neuron 1
Neuron 2
Output from
Neuron 1
Output from
Neuron 2
Artificial neural network
Natural NN
32. Evolutionary Systems
Genetic Programming:
A technique that follows Darwinian evolution.
The evolution takes place directly on the
programs in the population that are striving
to reach the goal specified by the
programmer.
Only the goal is known and possibly some
of the structure of the solution..
33. The concept of modern approach of AI
(Perception and action AI agent)
Organisms in the real world have gather information about
their
environment (perception) and
based on this information, they have to manipulate
their environment (including themselves) in a way
that is advantageous to them (action).
The action in turn may cause a change in the organism’s
perception, which can lead to a different type of action.
We call this the perception-action cycle.
Complex organisms do not just perceive and act, but they also
have an internal state that changes based on the success of
previous perception-action cycles.
This is the mechanism of learning.
34. AI “Application” Areas
Rule-Based Expert Systems
Medical Diagnosis: MYCIN, INTERNIST, PUFF
CSP Scheduling: ISIS, Airline scheduling
Data Mining
Financial: Fraud detection, credit scoring
Sales: Customer preferences, inventory
Science: NASA galaxy DB, genome
analysis
35. AI “Application” Areas (cont.)
Language Processing
Speech: dictation, HCI
Language: Machine Translation
ML & NLP: Fact Extraction
ML & words: Information Retrieval
Robotics
Machine Vision
Mobile Robots & “agents”
Manipulation
36. Applications
Game playing : Chess, Draughts,..
Speech recognition :speech to word processors
Understand natural language: understand meaning
of a whole sentence
Computer vision : 3-D world, but human eye and
camera are 2
Expert systems: stored knowledge
Robotics: space missions
Character recognition :handwriting
Pattern recognition: Faces, fingerprint,