Term
| Artificial intelligence (AI) |
|
Definition
-the branch of computer science that explores techniques for incorporating aspects of intelligence into computer systems
-the study and design of intelligent agents |
|
|
Term
|
Definition
-proposed test for intelligent behavior of machines
-allows a human to interrogate two entities, both hidden from the interrogator
-the objective is to be unable to distinguish between the two beyond random chance |
|
|
Term
|
Definition
| the study of how we as humans think and learn |
|
|
Term
|
Definition
**computers are better at these
-adding a column of numbers
-sorting a list of numbers into numerical order
-searching for a given name in a list of names
-managing a payroll
-calculating trajectory adjustments for the space shuttle |
|
|
Term
|
Definition
| **humans are better at these, sensory |
|
|
Term
|
Definition
**humans use a store house of experiences, involves images and cause and effect situations. Challenging for computers
-planning what to wear today
-deciding on the strategic direction a company should follow for the next 5 years
-running the triage center in a hospital emergency room after an earthquake |
|
|
Term
|
Definition
| a body of facts and truths |
|
|
Term
|
Definition
-knowledge representation scheme
-a paragraph or page of text that contains all the knowledge we are trying to capture is written in english, french, spanish, etc |
|
|
Term
|
Definition
-knowledge representation scheme
-language of formal logic, usually expressed symbolically
-sacrifices richness of expression for precision of expression |
|
|
Term
|
Definition
| knowledge represented as an image- a grid of pixels that have attributes of shading and color |
|
|
Term
|
Definition
-knowledge representation scheme
-not visual, but mathematical sense of a graph with nodes and connecting arcs |
|
|
Term
|
Definition
| type of graph used in graphical knowledge, rectangle nodes represent classes or objects, the oval nodes represent properties, and the arcs represent relationships |
|
|
Term
| Characteristics of Knowledge representation schemes |
|
Definition
-adequacy: must be adequate to capture all of the relevant info
-efficiency: avoiding redundant information wherever possible
-extendability: should be easy to extend the representation to include new knowledge
-appropriateness: should be appropriate for the knowledge domain being represented |
|
|
Term
|
Definition
| a cell capable of receiving stimuli in forms of electrochemical signals |
|
|
Term
|
Definition
| parts of a neuron that accept stimuli |
|
|
Term
|
Definition
| part of a neuron that sends stimuli to other neurons |
|
|
Term
|
Definition
| small gaps between the axon of one neuron and the dendrites of another neuron |
|
|
Term
| connectionist architecture |
|
Definition
| characterized by a large number of simple processors with multiple interconnections |
|
|
Term
| artificial neural networks/neural networks |
|
Definition
-created by stimulating individual neurons in hardware and connecting them in a massively parallel network of simple devices that act somewhat like biological neurons
-can learn from experience my modifying the weights on its connections
-can be given an initial set of weights an thresholds that are simply a first guess
-then presented with training data |
|
|
Term
|
Definition
| known correct outputs that are presented to a network |
|
|
Term
| back propagation algorithm |
|
Definition
| error estimates that are passed back from the output layer, eventually causes the network to settle into a stable state where it can correctly respond, to any desired degree of accuracy, to all inputs in the training set |
|
|
Term
|
Definition
| illustrates the possible next choices of items to search if the current item is not the target |
|
|
Term
|
Definition
| search domain is that after any one node has been searched, there are a huge number of next choices to try, and there is no algorithm to dictate the next choice |
|
|
Term
|
Definition
| takes us from the initial state to a winning configuration, and the graph nodes along the way represent the intermediate configurations. |
|
|
Term
|
Definition
-finds a solution path
-finds a winning sequence of moves for a board game, finds the shortest path through a network or finding the most successful investment strategy in the stock market |
|
|
Term
|
Definition
-"educated guess"
-evaluates the differences between the present state and the goal state and moves us to a new state that minimizes differences
-the state the maximizes our progress toward the goal state |
|
|
Term
|
Definition
| captures intelligent behavior by using simple agents that operate independently, can sense certain aspects of their environment, and can change their environment |
|
|
Term
|
Definition
| a form of software technology that is designed to interact collaboratively with a user somewhat in the mode of a personal assistant |
|
|
Term
|
Definition
| downloads your updated, personalized information, at periodic intervals, to your screen to be displayed whenever no other task is active |
|
|
Term
| expert systems/rule-based systems/knowledge-based systems |
|
Definition
-attempts to mimic the human ability to engage pertinent facts and string them together in a logical fashion to reach some conclusion
-must contain a knowledge base (a set of facts about the subject matter) and an inference engine (a mechanism for selecting the relevant facts and for reasoning from them in a logical way) |
|
|
Term
|
Definition
| reasoning process that gives methods for making new assertions |
|
|
Term
|
Definition
-inference engine for rule-based system
-begins with assertions and tries to match those assertions to the "if" clauses of rules, thereby generating new assertions. These may in turn be matched with "if" clauses, generating still more assertions |
|
|
Term
|
Definition
-inference engine for rule-based systems
-begins with a proposed conclusion and tries to match it with the "then" clauses of rules.
-It then looks at the corresponding "if" clauses and tries to match those with assertions, or with the "then" clauses of other rules.
-This process continues until all "if" clauses that arise have been successfully matched with assertions, in which case the proposed conclusion is justified, or until no match is possible, in which case the proposed conclusion is rejected |
|
|
Term
|
Definition
| allows the user to see the assertions and rules used in arriving at a conclusion, as a sort of check on the path of reasoning or for the user's own enlightenment |
|
|
Term
|
Definition
-builder of such a system acquires the info for the knowledge base by consulting "experts" in the domain and mining their expertise
-requires a great deal of interaction with the human expert, much of it in the domain environment |
|
|
Term
|
Definition
| a device, often human-like in form, that has the ability to gather sensory info from its surroundings and to autonomously perform mechanical actions of some sort in response |
|
|
Term
|
Definition
| says that the robot must have an internal representation of its environment and that its actions in response to some stimuli are programmed into the robot based on this model of the environment |
|
|
Term
|
Definition
| uses heuristic algorithms to allow the robot to respond directly to stimuli from its environment without filtering through some line of reasoning based on its internal understanding of that environment |
|
|
