Artificial Intelligence (AI) PDF

ARTIFICIAL INTELLIGENCE  WHAT IS INTELLIGENCE ? ❑ The exact definition of intelligence is complex and controversial. Psychologists have debated over an exact definition for years. ❑ One could certainly define intelligence by the properties one exhibits, for instance th...

ARTIFICIAL INTELLIGENCE  WHAT IS INTELLIGENCE ? ❑ The exact definition of intelligence is complex and controversial. Psychologists have debated over an exact definition for years. ❑ One could certainly define intelligence by the properties one exhibits, for instance the ability to: ✓ deal with new situation. ✓ solve problems. ✓ answer questions. ✓ devise plans, and so on.  ARTIFICIAL INTELLIGENCE: DEFINITIONS It is the science and engineering of Artificial intelligence is the study Simulation of Intelligence of systems that act in a way making intelligent machines, in machines. especially intelligent computer that to any observer would programs. appear to be intelligent.  ARTIFICIAL INTELLIGENCE AI is a collection of hard problems which can be solved by humans and other living things, but for which we don’t have good algorithms for solving. □ e. g., understanding spoken natural language, medical diagnosis, circuit design, learning, self-adaptation, reasoning, game playing, etc. A computer program that ▪ Acts like human (Turing test) ▪ Thinks like human (human-like patterns of thinking steps) ▪ Acts or thinks rationally (logically, correctly) The art of creating machines that perform functions that require intelligence when performed by humans.  GOALS OF AI ❑TO CREATE EXPERT SYSTEMS The systems which exhibit intelligent behavior, learn, demonstrate, explain, and advice its users. ❑ TO IMPLEMENT HUMAN INTELLIGENCE IN MACHINES Creating systems that understand, think, learn, and behave like humans.  STRONG & WEAK AI ❑ Weak AI, an artificial intelligence system which is only intended to be applicable on a specific kind of problem (e.g. computer chess) and not intended to display human-like intelligence in general. ❑ Siri is a good example of narrow intelligence. ▪ Siri operates within a limited pre-defiend range, there is no genuine intelligence, no self-awareness, no life despite being a sophisticated example of weak AI.  STRONG AND WEAK AI Strong AI is the intelligence of a machine that could successfully perform any intellectual task that a human being can. Strong AI also refers to as "full AI" or as the ability to perform "general intelligent action " The followers of strong AI believe that by giving a computer program sufficient processing power, and by providing it with enough intelligence, one can create a computer that can literally think and is conscious in the same way that a human is conscious. Examples : - The Turing Test (Turing) - The Robot College Student Test (Goertzel) - The Coffee Test (Goertzel) - The Employment Test (Nilsson)  NATURAL INTELLIGENCE AND AI ❑ Natural Intelligence is creative, while AI is uninspired. The ability to acquire knowledge is inherent in human mind, but with AI customized knowledge must be built into a carefully constructed system. ❑ Natural intelligence enables people to benefit from and use sensory experience directly, while AI mostly works on symbolic inputs. ❑ Natural intelligence is able to make reasons at all times by wide context of experience and bring it to bear on individual problems. While AI systems typically gain their power of knowledge by having a narrow focus of problem domain. ❑ Natural Intelligence is powerful but has limitations. Humans are intellectual but have limited knowledge bases, and information processing is comparably slow in brain when done with computers.  HOW AI WORKS: Think well Act well Think like humans Act like humans  HOW AI WORKS: Think well Develop formal models of knowledge representation, reasoning, learning, memory, problem solving that can be rendered in algorithms. Act well o For a given set of inputs, generate an appropriate output that is not necessarily correct but gets the job done. o A heuristic (heuristic rule, heuristic method) is a rule of thumb, strategy, trick, simplification, or any other kind of device which drastically limits search for solutions in large problem spaces.  HOW AI WORKS Think like humans o Cognitive science approach o Focus not just on behavior and I/O but also look at reasoning process. o Computational model should reflect “how” results were obtained. o GPS (General Problem Solver): Goal not just to produce humanlike behavior, but to produce a sequence of steps of the reasoning process that was similar to the steps followed by a person in solving the same task. Act like humans o Behaviorist approach. o Not interested in how you get results, just the similarity to what human results are.  TURING TEST Three rooms contain a person, a computer, and an interrogator. The interrogator can communicate with the other two. The interrogator tries to determine which the person is and which the machine is. The machine tries to fool the interrogator into believing that it is the person. If the machine succeeds, then we conclude that the machine can think.  AI APPLICATION AREAS Game Playing Automated Theorem Proving Natural Language Reasoning Processing Expert Systems Computer Vision Robotics Machine Learning  WHAT IS MACHINE LEARNING Machine learning is an application of artificial intelligence that involves algorithms and data that automatically analyse and make decision by itself without human intervention Therefore we can say in machine language artificial intelligence is generated on the basis of experience. It describes how computer perform tasks on their own by previous experiences. NORMAL COMPUTER VS ML The difference between normal computer software and machine learning is that a human developer hasn’t given codes that instructs the system how to react to situation, instead it is being trained by a large number of data. BEST PROGRAMMING LANGUAGES FOR ML Java C++ Shell Python R DIFFERENCE BETWEEN MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE AI iS a concept of creating intelligent machineS that StimulateS human behaviour whereaS Machine learning iS a SubSet of AI that allowS machine to learn from data without being programmed. ADVANTAGES OF MACHINE LEARNING Handling multi 01 Fast,Accurate, 03 dimensional Efficient data Automation of Enhanced cyber 02 most 04 security and applications spam detection  DISADVANTAGES OF MACHINE LEARNING It iS very difficult Interpretation of Data AcquiSition. to identify and reSultS RequireS more rectify the errorS. time and Space. END OF CHAPTER