Presentation is loading. Please wait.

Presentation is loading. Please wait.

ICT619 Intelligent Systems Unit Coordinator: Graham Mann Room 2.061 ECL Building Phone: 9360 7270

Similar presentations


Presentation on theme: "ICT619 Intelligent Systems Unit Coordinator: Graham Mann Room 2.061 ECL Building Phone: 9360 7270"— Presentation transcript:

1 ICT619 Intelligent Systems Unit Coordinator: Graham Mann Room 2.061 ECL Building Phone: 9360 7270 Email: g.mann@murdoch.edu.au @murdoch.edu.au

2 2 Unit aims to be aware of the rationale of the artificial intelligence and soft computing paradigms with their advantages over traditional computing to be aware of the rationale of the artificial intelligence and soft computing paradigms with their advantages over traditional computing to gain an understanding of the theoretical foundations of various types of intelligent systems technologies to a level adequate for achieving objectives as stated below to gain an understanding of the theoretical foundations of various types of intelligent systems technologies to a level adequate for achieving objectives as stated below to develop the ability to evaluate intelligent systems, and in particular, their suitability for specific applications to develop the ability to evaluate intelligent systems, and in particular, their suitability for specific applications to be able to manage the application of various tools available for developing intelligent systems to be able to manage the application of various tools available for developing intelligent systems

3 3 Unit delivery and learning structure 3 hours of lecture/workshop per week 3 hours of lecture/workshop per week Lecture/WS time will be spent discussing the relevant topic after an introduction by the lecturer Lecture/WS time will be spent discussing the relevant topic after an introduction by the lecturer Topic lecture notes will be available early in the week Topic lecture notes will be available early in the week Students should make use of the topic reading material in advance for the topic to be covered Students should make use of the topic reading material in advance for the topic to be covered Bringing up issues and questions for discussion are encouraged to create an interactive learning environment (this is assessed). Bringing up issues and questions for discussion are encouraged to create an interactive learning environment (this is assessed).

4 4 Resources and Textbooks Main text: Main text: Negnevitsky, M. Artificial Intelligence: A Guide to Intelligent Systems, 2005. 2nd Edition. Negnevitsky, M. Artificial Intelligence: A Guide to Intelligent Systems, 2005. 2nd Edition. The main text to be supplemented by chapters/articles from other books/journals/magazines as well as notes provided by the unit coordinator. The main text to be supplemented by chapters/articles from other books/journals/magazines as well as notes provided by the unit coordinator. A list of recommended readings and other resources will be provided for each topic. A list of recommended readings and other resources will be provided for each topic. Unit website: http://www.it.murdoch.edu.au/units/ICT619 will enable access to unit reading materials and links to other resources. Unit website: http://www.it.murdoch.edu.au/units/ICT619 will enable access to unit reading materials and links to other resources. http://www.it.murdoch.edu.au/units/ICT619

5 5 Assessment ACTIVITYDUEWEIGHT Workshop participation Continuous10% Project Week 12 35% Closed-book Exam Nov exams period 55%

6 6 Topic schedule Topic 1:Introduction to Intelligent Systems: Tools, Techniques and Applications Topic 1:Introduction to Intelligent Systems: Tools, Techniques and Applications Topic 2:Rule-Based Expert Systems Topic 2:Rule-Based Expert Systems Topic 3:Fuzzy Systems Topic 3:Fuzzy Systems Topic 4:Neural Computing Topic 4:Neural Computing Topic 5:Genetic Algorithms Topic 5:Genetic Algorithms Topic 6:Case-based Reasoning Topic 6:Case-based Reasoning Topic 7:Data Mining Topic 7:Data Mining Topic 8:Intelligent Software Agents Topic 8:Intelligent Software Agents Topic 9:Language Technology Topic 9:Language Technology

7 7 Topic 1: Introduction to Intelligent Systems What is an intelligent system? What is an intelligent system? Significance of intelligent systems in business Significance of intelligent systems in business Characteristics of intelligent systems Characteristics of intelligent systems The field of Artificial Intelligence (AI) The field of Artificial Intelligence (AI) The Soft Computing paradigm The Soft Computing paradigm An Overview of Intelligent System Methodologies An Overview of Intelligent System Methodologies Expert Systems Expert Systems Fuzzy Systems Fuzzy Systems Artificial Neural Networks Artificial Neural Networks Genetic Algorithms (GA) Genetic Algorithms (GA) Case-based reasoning (CBR) Case-based reasoning (CBR) Data Mining Data Mining Intelligent Software Agents Intelligent Software Agents Language Technology Language Technology

8 8 What is an intelligent system? What is intelligence? What is intelligence? Hard to define unless you list characteristics eg, Hard to define unless you list characteristics eg, Reasoning Reasoning Learning Learning Adaptivity Adaptivity A truly intelligent system adapts itself to deal with changes in problems (automatic learning) A truly intelligent system adapts itself to deal with changes in problems (automatic learning) Few machines can do that at present Few machines can do that at present Machine intelligence has a computer follow problem solving processes something like that in humans Machine intelligence has a computer follow problem solving processes something like that in humans Intelligent systems display machine-level intelligence, reasoning, often learning, not necessarily self-adapting Intelligent systems display machine-level intelligence, reasoning, often learning, not necessarily self-adapting

9 9 Intelligent systems in business Intelligent systems in business utilise one or more intelligence tools, usually to aid decision making Intelligent systems in business utilise one or more intelligence tools, usually to aid decision making Provides business intelligence to Provides business intelligence to Increase productivity Increase productivity Gain competitive advantage Gain competitive advantage Examples of business intelligence – information on Examples of business intelligence – information on Customer behaviour patterns Customer behaviour patterns Market trend Market trend Efficiency bottlenecks Efficiency bottlenecks Examples of successful intelligent systems applications in business: Examples of successful intelligent systems applications in business: Customer service (Customer Relations Modelling) Customer service (Customer Relations Modelling) Scheduling (eg Mine Operations) Scheduling (eg Mine Operations) Data mining Data mining Financial market prediction Financial market prediction Quality control Quality control

10 10 Intelligent systems in business – some examples HNC (now Fair Isaac) softwares credit card fraud detector Falcon offers 30-70% improvement over existing methods (an example of a neural network). HNC (now Fair Isaac) softwares credit card fraud detector Falcon offers 30-70% improvement over existing methods (an example of a neural network). MetLife insurance uses automated extraction of information from applications in MITA (an example of language technology use) MetLife insurance uses automated extraction of information from applications in MITA (an example of language technology use) Personalized, Internet-based TV listings (an intelligent agent) Personalized, Internet-based TV listings (an intelligent agent) Hyundais development apartment construction plans FASTrak- Apt (a Case Based Reasoning project) Hyundais development apartment construction plans FASTrak- Apt (a Case Based Reasoning project) US Occupational Safety and Health Administration (OSHA uses "expert advisors" to help identify fire and other safety hazards at work sites (an expert system). US Occupational Safety and Health Administration (OSHA uses "expert advisors" to help identify fire and other safety hazards at work sites (an expert system). Source: http://www.newsfactor.com/perl/story/16430.html

11 11 Characteristics of intelligent systems Possess one or more of these: Possess one or more of these: Capability to extract and store knowledge Capability to extract and store knowledge Human like reasoning process Human like reasoning process Learning from experience (or training) Learning from experience (or training) Dealing with imprecise expressions of facts Dealing with imprecise expressions of facts Finding solutions through processes similar to natural evolution Finding solutions through processes similar to natural evolution Recent trend Recent trend More sophisticated Interaction with the user through More sophisticated Interaction with the user through natural language understanding natural language understanding speech recognition and synthesis speech recognition and synthesis image analysis image analysis Most current intelligent systems are based on Most current intelligent systems are based on rule based expert systems rule based expert systems one or more of the methodologies belonging to soft computing one or more of the methodologies belonging to soft computing

12 12 The field of Artificial Intelligence (AI) Primary goal: Primary goal: Development of software aimed at enabling machines to solve problems through human-like reasoning Development of software aimed at enabling machines to solve problems through human-like reasoning Attempts to build systems based on a model of knowledge representation and processing in the human mind Attempts to build systems based on a model of knowledge representation and processing in the human mind Encompasses study of the brain to understand its structure and functions Encompasses study of the brain to understand its structure and functions In existence as a discipline since 1956 In existence as a discipline since 1956 Failed to live up to initial expectations due to Failed to live up to initial expectations due to inadequate understanding of intelligence, brain function inadequate understanding of intelligence, brain function complexity of problems to be solved complexity of problems to be solved Expert systems – an AI success story of the 80s Expert systems – an AI success story of the 80s Case Based Reasoning systems - partial success Case Based Reasoning systems - partial success

13 13 The Soft Computing (SC) paradigm Also known as Computational Intelligence Also known as Computational Intelligence Unlike conventional computing, SC techniques Unlike conventional computing, SC techniques 1.can be tolerant of imprecise, incomplete or corrupt input data 2.solve problems without explicit solution steps 3.learn the solution through repeated observation and adaptation 4.can handle information expressed in vague linguistic terms 5.arrive at an acceptable solution through evolution

14 14 The Soft Computing (SC) paradigm (contd) The first four characteristics are common in problem solving by individual humans The first four characteristics are common in problem solving by individual humans The fifth characteristic (evolution) is common in nature The fifth characteristic (evolution) is common in nature The predominant SC methodologies found in current intelligent systems are: The predominant SC methodologies found in current intelligent systems are: Artificial Neural Networks (ANN) Artificial Neural Networks (ANN) Fuzzy Systems Fuzzy Systems Genetic Algorithms (GA) Genetic Algorithms (GA)

15 15 Overview of Intelligent System Methodologies - Expert Systems (ES) Designed to solve problems in a specific domain, Designed to solve problems in a specific domain, eg, an ES to assist foreign currency traders eg, an ES to assist foreign currency traders Built by Built by interrogating domain experts interrogating domain experts storing acquired knowledge in a form suitable for solving problems, using simple reasoning storing acquired knowledge in a form suitable for solving problems, using simple reasoning Used by Used by Querying the user for problem-specific information Querying the user for problem-specific information Using the information to draw inferences from the knowledge base Using the information to draw inferences from the knowledge base Supplies answers or suggested ways to collect further inputs Supplies answers or suggested ways to collect further inputs

16 16 Overview of Expert Systems (contd) Usual form of the expert system knowledge base is a collection of IF … THEN … rules Usual form of the expert system knowledge base is a collection of IF … THEN … rules Note: not IF statements in procedural code Note: not IF statements in procedural code Some areas of ES application: Some areas of ES application: banking and finance (credit assessment, project viability) banking and finance (credit assessment, project viability) maintenance (diagnosis of machine faults) maintenance (diagnosis of machine faults) retail (suggest optimal purchasing pattern) retail (suggest optimal purchasing pattern) emergency services (equipment configuration) emergency services (equipment configuration) law (application of law in complex scenarios) law (application of law in complex scenarios)

17 17 Artificial Neural Networks (ANN) Human brain consists of 100 billion densely interconnected simple processing elements known as neurons Human brain consists of 100 billion densely interconnected simple processing elements known as neurons ANNs are based on a simplified model of the neurons and their operation ANNs are based on a simplified model of the neurons and their operation ANNs usually learn from experience – repeated presentation of example problems with their corresponding solutions ANNs usually learn from experience – repeated presentation of example problems with their corresponding solutions After learning the ANN is able to solve problems, even with newish input After learning the ANN is able to solve problems, even with newish input The learning phase may or may not involve human intervention (supervised vs unsupervised learning) The learning phase may or may not involve human intervention (supervised vs unsupervised learning) The problem solving 'model' developed remains implicit and unknown to the user The problem solving 'model' developed remains implicit and unknown to the user Particularly suitable for problems not prone to algorithmic solutions, eg, pattern recognition, decision support Particularly suitable for problems not prone to algorithmic solutions, eg, pattern recognition, decision support

18 18 Artificial Neural Networks (contd) Different models of ANNs depending on Different models of ANNs depending on Architecture Architecture learning method learning method other operational characteristics (eg type of activation function) other operational characteristics (eg type of activation function) Good at pattern recognition and classification problems Good at pattern recognition and classification problems Major strength - ability to handle previously unseen, incomplete or corrupted data Major strength - ability to handle previously unseen, incomplete or corrupted data Some application examples: Some application examples: - explosive detection at airports - face recognition - financial risk assessment - optimisation and scheduling

19 19 Genetic Algorithms (GA) Belongs to a broader field known as evolutionary computation Belongs to a broader field known as evolutionary computation Solution obtained by evolving solutions through a process consisting of Solution obtained by evolving solutions through a process consisting of survival of the fittest survival of the fittest crossbreeding, and crossbreeding, and mutation mutation A population of candidate solutions is initialised (the chromosomes) A population of candidate solutions is initialised (the chromosomes) New generations of solutions are produced beginning with the intial population, using specific genetic operations: selection, crossover and mutation New generations of solutions are produced beginning with the intial population, using specific genetic operations: selection, crossover and mutation

20 20 Genetic Algorithms (contd) Next generation of solutions produced from the current population using Next generation of solutions produced from the current population using crossover (splicing and joining peices of the solution from parents) and crossover (splicing and joining peices of the solution from parents) and mutation (random change in the parameters defining the solution) mutation (random change in the parameters defining the solution) The fitness of newly evolved solution evaluated using a fitness function The fitness of newly evolved solution evaluated using a fitness function The steps of solution generation and evaluation continue until an acceptable solution is found The steps of solution generation and evaluation continue until an acceptable solution is found GAs have been used in GAs have been used in portfolio optimisation portfolio optimisation bankruptcy prediction bankruptcy prediction financial forecasting financial forecasting design of jet engines design of jet engines scheduling scheduling

21 21 Fuzzy Systems Traditional logic is two-valued – any proposition is either true or false Traditional logic is two-valued – any proposition is either true or false Problem solving in real-life must deal with partially true or partially false propositions Problem solving in real-life must deal with partially true or partially false propositions Imposing precision may be difficult and lead to less than optimal solutions Imposing precision may be difficult and lead to less than optimal solutions Fuzzy systems handle imprecise information by assigning degrees of truth - using fuzzy logic Fuzzy systems handle imprecise information by assigning degrees of truth - using fuzzy logic

22 22 Fuzzy Systems (contd) FL allow us to express knowledge in vague linguistic terms FL allow us to express knowledge in vague linguistic terms Flexibility and power of fuzzy systems now well recognised (eg simplification of rules in control systems where imprecision is found) Flexibility and power of fuzzy systems now well recognised (eg simplification of rules in control systems where imprecision is found) Some applications of fuzzy systems: Some applications of fuzzy systems: Control of manufacturing processes Control of manufacturing processes appliances such as air conditioners, washing machines and video cameras appliances such as air conditioners, washing machines and video cameras Used in combination with other intelligent system methodologies to develop hybrid fuzzy-expert, neuro-fuzzy, Used in combination with other intelligent system methodologies to develop hybrid fuzzy-expert, neuro-fuzzy, or fuzzy-GA systems or fuzzy-GA systems

23 23 Case-based reasoning (CBR) CBR systems solve problems by making use of knowledge about similar problems encountered in the past CBR systems solve problems by making use of knowledge about similar problems encountered in the past The knowledge used in the past is built up as a case-base The knowledge used in the past is built up as a case-base CBR systems search the case-base for cases with attributes similar to given problem CBR systems search the case-base for cases with attributes similar to given problem A solution created by synthesizing similar cases, and adjusting to cater for differences between given problem and similar cases A solution created by synthesizing similar cases, and adjusting to cater for differences between given problem and similar cases Difficult to do well in practice, but very powerful if you can do it Difficult to do well in practice, but very powerful if you can do it

24 24 Case-based reasoning (contd) CBR systems can improve over time by learning from mistakes made with past problems CBR systems can improve over time by learning from mistakes made with past problems Application examples: Application examples: Utilisation of shop floor expertise in aircraft repairs Utilisation of shop floor expertise in aircraft repairs Legal reasoning Legal reasoning Dispute mediation Dispute mediation Data mining Data mining Fault diagnosis Fault diagnosis Scheduling Scheduling

25 25 Data mining The process of exploring and analysing data for discovering new and useful information The process of exploring and analysing data for discovering new and useful information Huge volumes of mostly point-of-sale (POS) data are generated or captured electronically every day, eg, Huge volumes of mostly point-of-sale (POS) data are generated or captured electronically every day, eg, data generated by bar code scanners data generated by bar code scanners customer call detail databases customer call detail databases web log files in e-commerce etc. web log files in e-commerce etc. Organizations are ending up with huge amounts of mostly day-to-day transaction data Organizations are ending up with huge amounts of mostly day-to-day transaction data

26 26 Data mining (contd) It is possible to extract useful information on market and customer behaviour by mining" the data It is possible to extract useful information on market and customer behaviour by mining" the data Note: This goes far beyond simple statistical analysis of numerical data, to classification and analysis of non-numerical data Note: This goes far beyond simple statistical analysis of numerical data, to classification and analysis of non-numerical data Such information might Such information might reveal important underlying trends and associations in market behaviour, and reveal important underlying trends and associations in market behaviour, and help gain competitive advantage by improving marketing effectiveness help gain competitive advantage by improving marketing effectiveness Techniques such as artificial neural networks and decision trees have made it possible to perform data mining involving large volumes of data (from "data warehouses"). Techniques such as artificial neural networks and decision trees have made it possible to perform data mining involving large volumes of data (from "data warehouses"). Growing interest in applying data mining in areas such direct target marketing campaigns, fraud detection, and development of models to aid in financial predictions, antiterrorism systems Growing interest in applying data mining in areas such direct target marketing campaigns, fraud detection, and development of models to aid in financial predictions, antiterrorism systems

27 27 Intelligent software agents (ISA) ISAs are computer programs that provide active assistance to information system users ISAs are computer programs that provide active assistance to information system users Help users cope with information overload Help users cope with information overload Act in many ways like a personal assistant to the user by attempting to adapt to the specific needs of the user Act in many ways like a personal assistant to the user by attempting to adapt to the specific needs of the user Capable of learning from the user as well as other intelligent software agents Capable of learning from the user as well as other intelligent software agents Application examples: Application examples: News and Email Collection, Filtering and Management News and Email Collection, Filtering and Management Online Shopping Online Shopping Event Notification Event Notification Personal scheduling Personal scheduling Online help desks, interactive characters Online help desks, interactive characters Rapid Response Implementation Rapid Response Implementation

28 28 Language Technology (LT) [The] application of knowledge about human language in computer- based solutions (Dale 2004) [The] application of knowledge about human language in computer- based solutions (Dale 2004) Communication between people and computers is an important aspect of any intelligent information system Communication between people and computers is an important aspect of any intelligent information system Applications of LT: Applications of LT: Natural Language Processing (NLP) Natural Language Processing (NLP) Knowledge Representation Knowledge Representation Speech recognition Speech recognition Optical character recognition (OCR) Optical character recognition (OCR) Handwriting recognition Handwriting recognition Machine translation Machine translation Text summarisation Text summarisation Speech synthesis Speech synthesis A LT-based system can be the front-end of information systems themselves based on other intelligence tools A LT-based system can be the front-end of information systems themselves based on other intelligence tools Hi, I am Cybelle. What is your name?

29 29 For Next Week Get hold of the textbook Get hold of the textbook Visit the library and find the section on artificial intelligence, browse some titles Visit the library and find the section on artificial intelligence, browse some titles Get onto the unit website, download and read papers concerning Expert Systems Get onto the unit website, download and read papers concerning Expert Systems We will study the theory and practice developing a simple expert system We will study the theory and practice developing a simple expert system Have a look at the AAAI Applications webpage at http://www.aaai.org/AITopics/html/applications.html Have a look at the AAAI Applications webpage at http://www.aaai.org/AITopics/html/applications.html


Download ppt "ICT619 Intelligent Systems Unit Coordinator: Graham Mann Room 2.061 ECL Building Phone: 9360 7270"

Similar presentations


Ads by Google