Posts: 6,566
Threads: 1,107
Joined: Jul 2011
Posts: 4,190
Threads: 817
Joined: Feb 2012
Artificial Intelligence full report
[attachment=17511]
Artificial Intelligence is the part of computer science concerned with designing intelligent computer systems, that is, systems that exhibit the characteristics we associate with intelligence in human behavior– understanding language, learning reasoning, solving problems and so on. Its main trust to development of computer system by relating human intelligence.
COGNITIVE SCIENCE APPLICATION
Cognitive science is the interdisciplinary scientific study of how information concerning faculties such as perception, language, reasoning, and emotion, is represented and transformed in a (human or other animal) nervous system or machine (e.g., computer).
OR
It focus on researching how human brain works and think and learn. The result of such research in human information processing for the development of variety of computer base application.
Expert System
An expert system is software that uses a knowledge base of human expertise for problem solving, or clarify uncertainties where normally one or more human experts would need to be consulted.
Advantage of Expert System
Scarce expertise made available.
Integration of expertise from different sources.
Improved quality (e.g. where an ES assists in design).
Ability to work with incomplete information.
Reduced system downtime (ES monitors or finds faults).
Training (users gain expertise from the ES).
Makes expertise available in remote locations.
ES can work faster than people.
Reliability (ES will not get tired or bored).
Posts: 4,190
Threads: 817
Joined: Feb 2012
Artificial Intelligence
[attachment=17703]
. INTRODUCTION :
Although there is no clear definition of AI (not even of intelligence), it can be described as the attempt to build machines that think and act like humans, that are able to learn and to use their knowledge to solve problems on their own.
A 'by-product' of the intensive studies of the human brain by AI researchers is a far better understanding of how it works.
The human brain consists of 10 to 100 billion neurons, each of which is connected to between 10 and 10,000 others through synapses. The single brain cell is comparatively slow (compared to a microprocessor) and has a very simple function: building the sum of its inputs and issuing an output, if that sum exceeds a certain value. Through its highly parallel way of operation, however, the human brain achieves a performance that has not been reached by computers yet; and even at the current speed of development in that field, we still have about twenty years until the first supercomputers will be of equal power.
In the meantime, a number of different approaches are tried to build models of the brain, with different levels of success.
The only test for intelligence there is, is the Turing Test.
A thinking machine has yet to be built.
2. WHY THE CURRENT APPROACH OF AI IS WRONG :
These following thoughts do not deal with technical problems of AI, nor am I going to prove that humans are the only intelligent species. What I want to show, is that the whole idea of AI needs to be changed in order to lead to more than just partial results.
2.1 Reference Points :
Today's AI concentrates entirely on the brain. If you look at the human body, however, it is not clear where to draw the line between which parts of the nervous system belong to the brain, and which don't. But a number of functions are performed by the spinal cord, for example, like withdrawing the hand quickly when touching something hot. It can be vitally important that this action is taken as fast as possible, in order to limit the damage. The only way of doing so is through reflexes, without the intervention of the brain. This is not an example of intelligent decisions outside the brain, but it provides an entry point to the following.
The Role of the Body :
The most obvious difference between man and other animals is his mind, his ability to accumulate knowledge and pass it on to his descendants. Yet many of man's highly developed abilities can be completely switched off by the sheer terror of a single aching tooth. This also applies for other strong feelings like hatred, grief or pain in general. They can make people act against their better knowledge and their principles - these being higher developed parts of the mind. This leads to a conclusion that is obvious from looking at the ancestry of man: the vital functions rule over everything else. Man has not been built to wear digital watches (as Douglas Addams states), but he is the winner of a game that is as old as life itself: Evolution. If people were able to simply ignore hunger, they would starve to death; if they would have to control their lungs consciously, they would sooner or later suffocate. Vital functions must have priority over everything else. Considering this, it is not surprising that many of our expressions involve basic needs, like 'being hungry for love', 'being tired of something', 'being fed up', 'having a bleeding heart', 'saving someone's skin'. This is also an example for what was said in the last paragraph: The main reference point is oneself, this is of course also true for strong emotions that are on a less 'basic' level.
Additionally, most (if not all) emotions are accompanied by physical symptoms, such as the production of hormones, shivering, gnashing of teeth or goose-pimples.
Posts: 4,190
Threads: 817
Joined: Feb 2012
Principles of Articial Intelligence
[attachment=17789]
Goal-Based Agents
In this chapter, we consider the design of goal-based agents. The specication and design of goal-based
agents involves answering the following questions:
1. What is the goal to be achieved? This involves describing a situation we want to achieve, a set of
properties that we want to hold (when the agent succeeds at its goal), etc. This requires dening a goal
test so which captures what it means to have achieved/satised the goal. While in some domains (e.g.,
chess) it is rather straightforward to specify the goal test, in others, it is not as obvious and requires
considerable thought. In general, the cognitive processes having to do with goal selection and goal
specication in humans and animals are poorly understood. Consequently, the design of autonomous
systems that select, prioritize, and update their goals is largely an unsolved problem in AI. In what
follows, we assume that the system designer or user will specify the goal to be achieved.
2. What are the actions that are available to the agent? We need to specify precisely all of the primitive
actions (including their preconditions and their expected eects on the environment) that are sucient
(at least in principle) to achieve the goal. Early AI systems assumed that given an action (also called
an operator) and a description of the current state of the world, the action completely species the
conditions under which the action can be applied to the current world as well as the the exact state
of the world after the action is executed in the current world. Actions were viewed as atomic, discrete
events that can be thought of as occurring at an instant in time. Thus, the world is in a state before the
action is executed, and it makes a transition to a dierent state (specied implicitly or explicitly by the
eects of the action) once the action is executed. For example, if \Mary is in class" and she performs
the action \go home" she will end up \at home."
2 Problem Solving as Search
A wide range of problems in AI|including, among others, theorem proving, game playing, planning, and
learning|can be formulated at an abstract level as essentially search problems.
As noted above, representation is a key issue in problem solving. Consider 17 sticks arranged in 6 squares
as shown in Figure 1. Suppose we are asked to remove just 5 sticks so that we are left with only 3 squares
(with no extra sticks). The number of possible ways is
5 . However, the problem could be represented as
that of removing 3 squares from the current conguration of 6 squares. The number of possibilities is just
3which is considerably smaller. Also note that the preceding discussion implicitly assumed that the squares
have to be of the same size. Thus, representation plays a key role in the formulation of search problems.
Pseudocode for a General Class of Search Algorithms
1. Let L = list of nodes yet to be examined (initialized to start node S).
2. If L is empty return FAIL.
Else, pick a node (n) in L.
3. If n is a goal node (i.e. n 2 G ), stop and return the path from S to n.
4. Otherwise remove the node n from L.
Add to L all of n's children labeling each with the corresponding path from
Return to step 2.
NOTE: If L is a queue we get BFS and if L is a stack we get DFS. In general, search algorithms dier
in terms of steps 2 and 4 are handled.
3.2 Analysis of Breadth-First Search and Depth-First Search
The search strategies are analyzed in terms of four criteria:
Space complexity: amount of memory during run-time
Time complexity: amount of time to nd a solution
Completeness: the search strategy is guaranteed to nd a solution, if one exists (at a nite depth)
Admissibility: the search strategy is guaranteed to nd the optimal (cheapest)solution if such a solu-
tion exists.
Posts: 4,190
Threads: 817
Joined: Feb 2012
Posts: 4,190
Threads: 817
Joined: Feb 2012