Slide 1: Slide 2: Definition of AI • Artificial Intelligence (AI) is the area of computer science focusing on creating machines that can engage on behaviors that humans consider intelligent. • Others define AI as “Artificial Intelligence, or AI for short, is a combination of computer science, physiology, and philosophy.”Slide 3: In order to classify machines as "thinking", it is necessary to define intelligence To what degree does intelligence consist of, for example, solving complex problems, or making generalizations and relationships? And what about perception and comprehension? Research into the areas of learning, of language, and of sensory perception have aided scientists in building intelligent machines. One of the most challenging approaches facing experts is building systems that mimicthe behavior of the human brain, made up of billions of neurons, and arguably the most complex matter in the universe.Slide 4: The Human Brain Probably the most desired result from an artificially intelligent system would be to simulate the working and the speed of the human brain. The brain cells consists of a lot of neurons and these neurons pass electrical impulses at very high speeds to the other neurons in the body. Messages gets transferred across these different neurons. Slide 5: Human Brain and AI The study of behavior, pattern and working of these neurons and its capabilities is a science altogether termed an neural networks.Slide 6: Human brain and AI The systems we are considering have the common features to the human brain • The messages passed are electrical • Both are capable of storing information • The speed with which the processor works is getting faster all the time but cannot get closer to the brain. • All the reactions, responses and relating done by the brain are due to some intrinsic or acquired knowledge.Slide 7: History of AI • Artificial Intelligence has come a long way from its early roots, driven by dedicated researchers. The beginnings of AI reach back before electronics, to philosophers and mathematicians such as George Boole and others theorizing on principles that were used as the foundation of AI Logic. AI really began to intrigue researchers with the invention of the computer in 1943. The technology was finally available, or so it seemed, to simulate intelligent behavior.Slide 8: The Time Line of AISlide 9: The Turing Test You enter a room and encounter two terminals: one terminal connects with a computer, and the other interfaces with a person who types responses. The goal of the test is for you to determine which terminal is connected with the computer. You are allowed to ask questions, make assertions, question feelings and motivations for as long as you wish. If you fail to determine which terminal is communicating with the computer or guess that the computer is the human, the computer has passed the test and can be said to be `conscious'. Slide 10: Approaches to AI • Using principles of boolean algebra was the most primary step in realizing AI. On the level of a single neuron, the release or failure to release an impulse was the basis by which the brain makes true / false decisions. • Applying principles of neural networks which is basically creating electronic CKTs to show how electronic networks could generate logical processes. It is also stated that neural networks may, in the future, be able to learn, and recognize patterns. Slide 11: Approaches to AI • Artificial neural networks have presented some impressive results . Frank Rosenblatt, experimenting with computer simulated networks, was able to create a machine that could mimic the human thinking process, and recognize letters. • Expert systems or Top down approach-Because of the large storage capacity of computers, expert systems had the potential to interpret statistics, in order to formulate rules. It is one of the most popular approaches to AISlide 12: Expert Systems • An expert system works much like a detective solves a mystery. Using the information, and logic or rules, an expert system can solve the problem. For example if the expert system was designed to distinguish birds it may have the following: Slide 13: Limitations to Development of AI • Expense of constructing a machine to simulate neurons, it was expensive even to construct neural networks with the number of neurons in an ant. • The second factor is current computer architecture. The standard Von Neuman computer, the architecture of nearly all computers, lacks an adequate number of pathways between components. Researchers are now developing alternate architectures for use with neural networks. Slide 14: Classification Of Knowledge One of the toughest constraints in achieving AI is the lack of good techniques for classifying human intelligence.one such method is called frames Pioneered by Marvin Minsky, frame theory revolves around packets of information. For example, say the situation was a birthday party. A computer could call on its birthday frame, and use the information contained in the frame, to apply to the situation. The computer knows that there is usually cake and presents because of the information contained in the knowledge frame. Frames can also overlap, or contain sub-frames. The use of frames also allows the computer to add knowledge. Although not embraced by all AI developers, frames have been used in comprehension programs such as SAM.Slide 15: Different practices of AI • The study of “rational” behavior and processing. • The study of human behavior and cognitive processing. • The study of other approaches: neural, evolutionary. • Computational models of component processes: knowledge bases, inference engines, search techniques, machine learning techniques. • Understanding the connection between domains & techniques. – Computational constraints vs. desired behavior. • Application of techniques to real world problems.Slide 16: Role of AI in Games Gaming has become one of the biggest sectors in the computer industry. A survey by the magazine Gaming world showed that at any instant of time at least 250,000 people would be playing games on a computer. With development of team based games played over the internet, gaming has taken excitement to a whole new level. Slide 17: What can AI control in Games • Opponents • Teammates • Strategic Opponents • Support Characters • Autonomous Characters • Commentators • Camera Control • Plot and Story Guides/DirectorsSlide 18: Goals of AI action game opponent *Provide a challenging opponent Not always as challenging as a human – ex: Quake monsters. What ways should it be subhuman? *Not too challenging. Should not be superhuman in accuracy, precision, sensing, ... Should not be too predictable. *Through randomness. Through multiple, fine-grained responses. Through adaptation and learning.Slide 19: Use of an AI Agent • Each time through control loop, “tick” each agent. • Define an API for agents: sensing and acting. • Encapsulate all agent data structures. – And so agents can’t trash each other or the game. – Share global data structures on maps, etc. Agent 1 Agent 2 Player GameSlide 20: Determining Simple Behavior Random motion Just roll the dice to pick when and which direction to move Simple pattern Follow invisible tracks: Galaxians Tracking Pure Pursuit: Move toward agent’s current position Head seeking missile Lead Pursuit: Move to position in front of agent Collision: Move toward where agent will be Weave: Every N seconds move X degree off opponent’s bearing Spiral: Head 90-M degrees off of opponent’s bearing Evasive – opposite of any tracking Delay in sensing gives different effectsSlide 21: Some Examples Random FunctionSlide 22: Simple PatternsSlide 23: Pure PursuitSlide 24: Lead PursuitSlide 25: Collision CourseSlide 26: Moving Towards goal SourceSlide 27: Other Strategies Include • Using Finite State Machines • Using the decision trees. Outlook? Sunny Overcast Rain NoTemp? Wind? Hot Cool Mild No Yes Yes Weak Strong Yes NoSlide 28: • Sense – Gather input sensor changes – Update state with new values • Think – Poll each decision tree • Act – Execute any changes to actions Sense Think ActSlide 29: Learning Decision Trees • Decision trees are usually learned by induction – Generalize from examples – Induction doesn’t guarantee correct decision trees • Bias towards smaller decision trees – Occam’s Razor: Prefer simplest theory that fits the data – Too expensive to find the very smallest decision tree • Learning is non-incremental – Need to store all the examples • ID3 is the basic learning algorithm – C4.5 is an updated and extended versionSlide 30: Conclusion AI is being used in every little system now. It will only be a matter of time when AI becomes a reality. There a loads of intelligent systems that we use everyday like search engines, IDE enhancements. Even software's like MS Word have intelligent agents working which inform us about spelling and grammatical mistakes . AI systems are the next influential step for the future.