Basic Introduction to Artificial Intelligence PDF

Artificial Intelligence Artificial Intelligence (AI) refers to the capability of machines, typically computer systems, to perform tasks that would typically require human intelligence. These tasks encompass a broad range of activities, including problem-solving, learning, reasoning, perce...

Artificial Intelligence Artificial Intelligence (AI) refers to the capability of machines, typically computer systems, to perform tasks that would typically require human intelligence. These tasks encompass a broad range of activities, including problem-solving, learning, reasoning, perception, natural language understanding, and decision-making. AI systems are designed to mimic or simulate human cognitive functions, enabling them to analyze data, adapt to changing conditions, and make informed choices. AI systems rely on algorithms and data to process information and improve their performance over time. Machine learning, a subset of AI, involves training algorithms on large datasets to recognize patterns and make predictions or decisions based on new data. COM 316 Robot Teams USC robotics Lab COM 316  What is AI? (Some Definitions of AI, Organized into 4 Categories) Systems that think like Systems that think rationally human “The exciting new effort to make “The study of mental faculties through computers thinks … machine with minds, the use of computational models” in the full and literal sense” (Haugeland (Charniak et al. 1985) 1985) “The study of the computations that make “The automation of activities that we it possible to perceive,reason, and act.” associate with human thinking, activities: (Winston 1992) decision-making, problem-solving, learning….” (Bellman 1978) Systems that act like human Systems that act rationally “The art of creating machines that A field of study that seeks to explain and perform functions that require emulate intelligent behavior in terms of intelligence when performed by people” computational processes” (Schalkol, (Kurzweil, 1990) 1990) “The study of how to make computers do “AI ….. Is concerned with intelligent things at which, at the moment, people behavior in artifacts.” (Nilsson 1998) are better.” (Rich&Knight 1991) COM 316 What is AI? (Some Definitions of AI, Organized into 4 Categories) Theses definitions vary along two dimentions: 1. Thought Processes and Reasoning (thinking) 2. Behavior (acting) The definitions on the left measure success in terms of fidelity to human performance The definitions on the right measure against an ideal concept of intelligence, which is called Rationality. A system is rational if it does the “right thing”, given what it knows. COM 316 What is AI? Four Approches Human-centered approaches (Empirical Science) that involves : Hypothesis and Experimental confirmation Acting Humanly: The Turing Test Thinking Humanly: Cognitive Science Rationalist approach that involves: Combination of Mathematics and Engineering Thinking Rationally: Laws of Thought Acting Rationally: The Rational Agent COM 316 Acting Humanly: The Turing Test Alan Turing's 1950 article Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent “Can machines think?”  “Can machines behave ntelligently?” The Turing test (The Imitation Game): Operational definition of intelligence. COM 316 Versions of the Turing test : Imitation Game Turing's original game described a simple party game involving three players: Player A is a man, player B is a woman and player C (who plays the role of the interrogator) is of either sex. In the Imitation Game, player C is unable to see either player A or player B, and can communicate with them only through written notes. By asking questions to both players, player C tries to determine which of the two is the man and which is the woman. Player A's role is to trick the interrogator into making the wrong decision, while player B attempts to assist the interrogator in making the right one. Turing proposed : that the role of player A be filled by a computer so that its task was to pretend to be a woman and attempt to trick the interrogator into making an incorrect evaluation. The success of the computer was determined by comparing the outcome of the game when player A is a computer against the outcome when player A is a man. Turing stated : if "the interrogator decide wrongly as often when the game is played [with the computer] as he does when the game is played between a man and a woman", it may be argued that the computer is intelligent. COM 316 Acting Humanly: The Turing Test What computer needs to possess: Natural language processing, Knowledge representation, Automated reasoning, and Machine learning Are there any problems/limitations to the Turing Test? COM 316 What tasks require AI? “AI is the science and engineering of making intelligent machines which can perform tasks that require intelligence when performed by humans …” COM 316 What tasks require AI? Tasks that require AI: Solving a differential equation Brain surgery Inventing stuff Playing Jeopardy Playing Wheel of Fortune What about walking? What about grabbing stuff? What about pulling your hand away from fire? What about watching TV? What about day dreaming? COM 316 The Full Turing Test : Standard interpretation "standard interpretation." In this version, player A is a computer and player B a person of either sex. The role of the interrogator is not to determine which is male and which is female, but which is a computer and which is a human. The fundamental issue with the standard interpretation is that the interrogator cannot differentiate which responder is human, and which is machine. There are issues about duration, but the standard interpretation generally considers this limitation as something that should be reasonable. COM 316  Acting Humanly: The Full Turing Test Problem: 1) Turing test is not reproducible, constructive, and amenable to mathematic analysis. 2) What about physical interaction with interrogator and environment? Trap door COM 316 What would a computer need to pass the Turing test? Natural language processing: to communicate with examiner. Knowledge representation: to store and retrieve information provided before or during interrogation. Automated reasoning: to use the stored information to answer questions and to draw new conclusions. Machine learning: to adapt to new circumstances and to detect and extrapolate patterns. COM 316 What would a computer need to pass the Turing test? Vision (for Total Turing test): to recognize the examiner’s actions and various objects presented by the examiner. Motor control (total test): to act upon objects as requested. Other senses (total test): such as audition, smell, touch, etc. COM 316 Thinking Humanly: Cognitive Science 1960 “Cognitive Revolution”: information- processing psychology replaced behaviorism Cognitive science brings together theories and experimental evidence to model internal activities of the brain What level of abstraction? “Knowledge” or “Circuits”? How to validate models? Predicting and testing behavior of human subjects (top-down) Direct identification from neurological data (bottom-up) Building computer/machine simulated models and reproduce results (simulation) COM 316 What is Cognitive Science About? How information is represented, processed, and transformed (in faculties such as perception, language, memory, attention, reasoning, and emotion) within nervous systems (humans or other animals) and machines (e.g. computers). Cognitive science consists of multiple research disciplines, including psychology, artificial intelligence, philosophy, neuroscience, linguistics, and anthropology. It spans many levels of analysis, from low-level learning and decision mechanisms to high-level logic and planning; from neural circuitry to modular brain organization. The fundamental concept of cognitive science is that "thinking can best be understood in terms of: (1) representational structures in the mind and (2) computational procedures that operate on those structures."[ COM 316 Thinking Rationally: Laws of Thought Aristotle (~ 450 B.C.) attempted to codify “right thinking” What are correct arguments/thought processes? E.g., “Socrates is a man, all men are mortal; therefore Socrates is mortal” Several Greek schools developed various forms of logic: notation plus rules of derivation for thoughts. COM 316 Thinking Rationally: Laws of Thought Problems: 1)Uncertainty: Not all facts are certain (e.g., the flight might be delayed). 2)Resource limitations: - Not enough time to compute/process - Insufficient memory/disk/etc - Etc. COM 316 Acting Rationally: The Rational Agent Rational behavior: Doing the right thing! The right thing: That which is expected to maximize the expected return Provides the most general view of AI because it includes: Correct inference (“Laws of thought”) Uncertainty handling Resource limitation considerations (e.g., reflex vs. deliberation) Cognitive skills (NLP, AR, knowledge representation, ML, etc.) Advantages: 1) More general 2) Its goal of rationality is well defined COM 316 How to achieve AI? How is AI research done? AI research has both theoretical and experimental sides. The experimental side has both basic and applied aspects. There are two main lines of research: One is biological, based on the idea that since humans are intelligent, AI should study humans and imitate their psychology or physiology. The other is phenomenal, based on studying and formalizing common sense facts about the world and the problems that the world presents to the achievement of goals. The two approaches interact to some extent, and both should eventually succeed. It is a race, but both racers seem to be walking. [John McCarthy] COM 316 Branches of AI Logical AI Search Natural language processing pattern recognition Knowledge representation Inference From some facts, others can be inferred. Automated reasoning Learning from experience Planning To generate a strategy for achieving some goal Epistemology Study of the kinds of knowledge that are required for solving problems in the world. Ontology Study of the kinds of things that exist. In AI, the programs and sentences deal with various kinds of objects, and we study what these kinds are and what their basic properties are. Genetic programming Emotions??? … COM 316 AI Prehistory COM 316 AI History COM 316 AI State of the art Have the following been achieved by AI? World-class chess playing Playing table tennis Cross-country driving Solving mathematical problems Discover and prove mathematical theories Engage in a meaningful conversation Understand spoken language Observe and understand human emotions Express emotions … COM 316 A driving example: Beobots Goal: build robots that can operate in unconstrained environments and that can solve a wide variety of tasks. COM 316 Beowulf + robot = “Beobot” COM 316 A driving example: Beobots Goal: build robots that can operate in unconstrained environments and that can solve a wide variety of tasks. We have: Lots of CPU power Prototype robotics platform Visual system to find interesting objects in the world Visual system to recognize/identify some of these objects Visual system to know the type of scenery the robot is in We need to: Build an internal representation of the world Understand what the user wants Act upon user requests / solve user problems COM 316  The basic components of vision + Original Downscaled Segmented Riesenhuber & Poggio, Scene Layout Nat Neurosci, 1999 & Gist Localized Object Recognition Attention COM 316 COM 316  Beowulf + Robot = “Beobot” COM 316 Main challenge: extract the “minimal subscene” (i.e., small number of objects and actions) that is relevant to present behavior from the noisy attentional scanpaths. Achieve representation for it that is robust and stable against noise, world motion, COMand 316egomotion.  Prototype Stripped-down version of proposed general system, for simplified goal: drive around USC olympic track, avoiding obstacles Operates at 30fps on quad-CPU Beobot; Layout & saliency very robust; Object recognition often confused by background clutter. COM 316  Major issues How to represent knowledge about the world? How to react to new perceived events? How to integrate new percepts to past experience? How to understand the user? How to optimize balance between user goals & environment constraints? How to use reasoning to decide on the best course of action? How to communicate back with the user? How to plan ahead? How to learn from experience? COM 316 Outlook AI is a very exciting area right now. This course will teach you the foundations. In addition, we will use the Beobot example to reflect on how this foundation could be put to work in a large-scale, real system. COM 316