Introduction to intelligent systems
0 likes2,825 views
The document provides an introduction to intelligent systems, defining their properties and characteristics, such as operation in complex environments, primary cognitive abilities, and complex intelligent behavior. It discusses the importance of sensors and actuators in these systems, as well as their ability to learn and adapt through experience. The content is aimed at systems engineers and highlights various applications and cognitive abilities relevant to intelligent systems.
![Act
[Heat/not heat]
Sense
[Room temperature]
Performance measure
[Energy consumption]
Environment
[House]
Example: Thermostat
Communication
[Manual controller]
Thermostat
6](https://image.slidesharecdn.com/introductiontointelligentsystems-200930152015/85/Introduction-to-intelligent-systems-7-320.jpg)
![There are different properties that define the complexity
of the environment with respect to the system
• Static / dynamic
The environment (doesn’t change / changes) while an
agent is deliberating
• Discrete / continuous
The state of the environment, time, percepts or actions
(are discrete / are continuous)
• Fully-observable / partial-observable
Sensors (detect / don’t detect) all aspects that are
relevant to the choice of action
• Deterministic / stochastic
The next state of the environment (is / isn’t) completely
determined by the current state and the action
• Episodic / sequential
Actions (don’t influence / influence) future actions
• Known / unknown
The outcomes for actions (are known / are not
known) by the agent in advance
[Russell, Norvig, 2009]
Act
Sense
Environment
Intelligent
system
8Russell, S., Norvig P. (2009). Artificial Intelligence: A Modern Approach (3rd edition). Pearsons Education Limited.](https://image.slidesharecdn.com/introductiontointelligentsystems-200930152015/85/Introduction-to-intelligent-systems-9-320.jpg)
Introduction to intelligent systems
- 1. Introduction to Intelligent Systems Course: Intelligent Systems Martin Molina 2020
- 2. • Specialized tasks in professional domains – Medical diagnosis (e.g., recognize tumors on x-ray images) – Airport gate assignment • Tedious tasks – Autonomous car driving – Domestic tasks (e.g., house cleaning) • Dangerous tasks – Exploration of unknown areas (e.g., underwater exploration) What do we mean by intelligent system? 1 Examples of tasks: We may see an intelligent system as a tool designed to perform tasks for us that require intelligence
- 3. 2 • We are not interested in deciding whether a system is intelligent or not • We are interested in having tools for systems engineers We are in an engineering context Engineers who need to conceive, analyze, design and program efficiently intelligent systems Tools like design metaphors, architectural patterns, computational methods and software tools
- 4. How can we characterize an intelligent system? We can distinguish three main properties: 1. Working in a complex world 2. Primary cognitive abilities (e.g., perception, language use, etc.) 3. Complex intelligent behavior (e.g., rationality, learning, etc.) 3 Molina, Martin (2020). What is an intelligent system?. ArXiv preprint arXiv:2009.09083 https://arxiv.org/pdf/2009.09083.pdf
- 5. How can we characterize an intelligent system? We can distinguish three main properties: 1. Working in a complex world 2. Primary cognitive abilities (e.g., perception, language use, etc.) 3. Complex intelligent behavior (e.g., rationality, learning, etc.) 4
- 6. Property 1: Working in a complex world • An intelligent system operates in an environment and interacts with other agents (a user or other individuals) • The system observes features from the environment through sensors and performs actions using actuators • The use of sensors and actuators (real or virtual) separates the body of the intelligent system from the rest of the environment (“embodiment”) 5 Sensors Actuators Act Sense Environment Intelligent system Sensors Actuators Communicate Other agents
- 7. Act [Heat/not heat] Sense [Room temperature] Performance measure [Energy consumption] Environment [House] Example: Thermostat Communication [Manual controller] Thermostat 6
- 8. System Environment User Observable features Actions Performance measure Self-driving car Roads, cars, pedestrians, … Passenger Images from cameras, coordinates from GPS, speed Steering, accelerator, brake, signal, horn Safety, travel time, comfort, fuel consumption Medical diagnosis system Patients Physician Test results, medical history, etc. Drug prescriptions, proposed tests Health, costs of tests and treatment Chemistry tutor system Chemistry students Instructor Answers given by students Tests, proposed exercises, proposed readings Student’s score on tests Other examples 7
- 9. There are different properties that define the complexity of the environment with respect to the system • Static / dynamic The environment (doesn’t change / changes) while an agent is deliberating • Discrete / continuous The state of the environment, time, percepts or actions (are discrete / are continuous) • Fully-observable / partial-observable Sensors (detect / don’t detect) all aspects that are relevant to the choice of action • Deterministic / stochastic The next state of the environment (is / isn’t) completely determined by the current state and the action • Episodic / sequential Actions (don’t influence / influence) future actions • Known / unknown The outcomes for actions (are known / are not known) by the agent in advance [Russell, Norvig, 2009] Act Sense Environment Intelligent system 8Russell, S., Norvig P. (2009). Artificial Intelligence: A Modern Approach (3rd edition). Pearsons Education Limited.
- 10. • Static / dynamic • Discrete / continuous • Fully-observable / partial-observable • Deterministic / stochastic • Episodic / sequential • Known / unknown Chess player Example: Environment of a chess player 9
- 11. • Static / dynamic • Discrete / continuous • Fully-observable / partial-observable • Deterministic / stochastic • Episodic / sequential • Known / unknown Self-driving car Example: Environment of a self-driving car 10
- 12. How can we characterize an intelligent system? We can distinguish three main properties: 1. Working in a complex world 2. Primary cognitive abilities (e.g., perception, language use, etc.) 3. Complex intelligent behavior (e.g., rationality, learning, etc.) 11
- 13. 12 Carroll, J. B. (1993). Human cognitive abilities: A survey of factor-analytic studies. Cambridge University Press. John B. Carroll Professor of Psychology University of Chicago (1920 -2003) We can identify multiple cognitive abilities 1993 Cognitive ability: Ability that requires to process mental information
- 14. We follow a pragmatic engineering approach to identify cognitive abilities • We identify abilities that: – Are common in computer systems – Can be implemented with AI methods • We consider two separated levels: – Primary abilities (basic abilities) – Secondary abilities (abilities that use models of other abilities) 13
- 15. Environment Other agents Reasoning about the world and making decisions about what to do Deliberation Action control Perception Interaction Control the execution of the own actions Extraction of relevant data from the observed world Interaction with other agents (e.g., using language) Property 2: Primary cognitive abilities 14
- 16. Interaction (Passenger requests destination) Passenger Steering Pedes- trians Traffic signals Vehicles Accele- ration Braking Environment Example: Autonomous car Deliberation (Path planning to reach the requested destination) Perception Action control Data extraction from ultrasonic sensors, radar, lidar, camera and GPS Control of driving mechanisms 15
- 17. Interaction Other agents A1P1 P2 Pm A2 An Environment Perception and action control are usually divided in multiple components Deliberation Perception Action control 16 Parallel Serial
- 18. Gap Interaction P1 P2 Pm Environment Deliberation Perception Action control Attention mechanisms Symbol grounding Execution control Cognizant failure The gap between deliberation and perception-actuation requires specific abilities Other agents 17 A1 A2 An
- 19. Environment Other agents Deliberation Action control Perception Interaction 18 Reactive behavior Generation of instantaneous actions in response to a stimulus (e.g., animal reflexes or in decisions based on intuitions). Advantage: • Efficient reaction to dynamic events in a dynamic environment (it uses limited memory about the world) Deliberation Making decisions about what to do based on justifiable reasons Advantages: • Reactive behaviors can be inhibited to reach more useful long-term goals • Decisions are consistent with own knowledge “Action control” provides “reactive behavior”
- 20. Advisor system • Helps the user to act in the environment • The user makes decisions about what to do Autonomous system • Acts in the environment to help the user • The system makes decisions about what to do Help me perform task T Perform task T for me We can distinguish two types of systems according to who acts in the environment Act Sense SuggestionCompletion Environ- ment Intelligent advisor system User Act Sense Environ- ment Intelligent autonomous system User 19 (a) (b)
- 21. An intelligent system may interact with other system Request Answer Act Sense Environ- ment 1 Intelligent system 1 20 Act Sense Environ- ment 2 Intelligent system 2
- 22. Intelligent systems can be part of multiagent systems creating complex organizations Partial environment Partial environment Partial environment Partial environment Partial environment Global environment Agent Agent Agent Agent Agent 21 Sense and act Sense and act Sense and act Sense and act Sense and act Communicate Communicate Communicate Communicate Communicate Communicate
- 23. How can we characterize an intelligent system? We can distinguish three main properties: 1. Working in a complex world 2. Primary cognitive abilities (e.g., perception, language use, etc.) 3. Complex intelligent behavior (e.g., rationality, learning, etc.) 22
- 24. Environment Other agents Deliberation Action control Perception Interaction Property 3: Complex intelligent behavior 3.1. Acting rationally 3.2. Adaptation through learning 3.3. Introspection 23
- 25. A system acts rationally if it makes decisions to obtain the maximum performance measure Examples: • A chess player selects the movement that maximizes the expectation of winning the game • A self-driving car selects the best route to reach a destination considering possible traffic jams Implementation: • The expected performance measure of actions is usually uncertain • Rational behavior can be explicitly programmed using algorithms from decision theory (with a probabilistic representation) 24 Sub-property 3.1: Acting rationally
- 26. 25 Rational decisions affect different cognitive abilities Environment Other agents Deliberation Action control Perception Interaction What is the next question to ask the user?, … What part of the environment requires more attention?, … What is the right action to do?, what is the right method to perform a task?, … What is the right method to control an action?, …
- 27. The system is capable of improving its performance over multiple interactions with the world Examples: • A chess player improves its capacity to win by learning from game experience • A self-driving car reduces the time to reach destination in a city by learning from the experience of urban trips 26 Sub-property 3.2: Adaptation through learning
- 28. 27 Adaptation through learning can affect different cognitive abilities Environment Other agents Deliberation Action control Perception Interaction Learning user preferences, … Learning relevance of features, … Learning by deduction using a world model, … Improving action control by learning (object manipulation, …)
- 29. • Capacity to analyze one's cognitive abilities – The system uses an observable model of its own abilities – This model is used to simulate self-awareness processes Practical utility: • Allows the system to judge its own actions – This provides feedback to be able to learn (this feedback can also be done by simulating reactive feelings) • Allows the system to generate explanations – E.g., the system is able to justify recommended decisions to the user 28 Sub-property 3.3: Introspection
- 30. Summary of properties of an intelligent system 1. Working in a complex world – Environment – Other agents (e.g., user) 2. Primary cognitive abilities – Perception – Action control – Deliberation – Interaction 3. Complex intelligent behavior – Acting rationally – Adaptation through learning – Introspection 29 Environment Other agents Deliberation Action control Perception Interaction • Acting rationally • Adaptation through learning • Introspection Intelligent system
- 31. Scientific journals • IEEE intelligent systems (IEEE) • Knowlegde-based systems (Elsevier) • Expert systems with applications (Elsevier) • Engineering applications of artificial intelligence (Elsevier) • International journal on artificial intelligence tools (World Scientific) Associations • AAAI: http://aaai.org • ECCAI: http://www.eccai.org There are multiple sources of information about intelligent systems 30
- 32. Lecture slides of master course “Intelligent Systems”. © 2020 Martin Molina This work is licensed under Creative Commons license CC BY-SA 4.0: https://creativecommons.org/licenses/by-sa/4.0/legalcode Suggested work citation: Molina, M. (2020): “Intelligent Systems”. Master course (lecture slides). Department of Artificial Intelligence. Universidad Politécnica de Madrid. 31