AIMA 2nd Edition Chapter 1: Artificial Intelligence
empiricism
"Nothing is in the understanding, which was not first in the senses."
physical symbol system
"a physical symbol system has the necessary and sufficient means for general intelligent action."
utility
"preferred outcomes"
robotics
(Part of the Total Turing Test) Computer capability to manipulate objects and move about.
computer vision
(Part of the Total Turing Test) Computer capability to perceive objects
machine learning
(Part of the Turing Test) Computer capability to adapt to new circumstances and to detect and extrapolate patterns
natural language processing
(Part of the Turing Test) Computer capability to enable it to communicate successfully in English.
knowledge representation
(Part of the Turing Test) Computer capability to store what it knows or hears.
automated reasoning
(Part of the Turing Test) Computer capability to use the stored information to answer questions and to draw new conclusions
machine evolution
(now called genetic algorithms) were based on the undoubtedly correct belief that by making an appropriate series of small mutations to a machine code program, one can generate a program with good performance for any particular simple task.
materialism
An alternative to dualism is _________, which holds that the brain's operation according to the laws of physics constitutes the mind.
probability
Besides logic and computation, the third great contribution of mathematics to A1 is the theory of _________
dualism
Descartes held that there is a part of the human mind (or soul or spirit) that is outside of nature, exempt from physical laws
NP-completeness
How can one recognize an intractable problem?
Total Turing Test
It includes a video signal so that the interrogator can test the subject's perceptual abilities, as well as the opportunity for the interrogator to pass physical objects "through the hatch."
limited rationality
It is acting appropriately when there is not enough time to do all the comiputations one might like.
agent
It is just something that acts. But are expected to have other attributes that distinguish them from mere "programs," such as operating under autonomous control, perceiving their environment, persisting over a prolonged time period, adapting to change, and being capable of taking on another's goals. (comes from the Latin agere, "to do")
rational agent
It is one that acts so as to achieve the best outcome or, when there is uncertainty, the best expected outcome.
syllogisms
It provided patterns for argument structures that always yielded correct conclusions when given correct premises and was formulated by Aristotle. eg. "Socrates is a man; all men are mortal; therefore, Socrates is mortal."
Turing Test
It was designed to provide a satisfactory operational definition of intelligence.
certainty factors
MYCIN incorporated a calculus of uncertainty called _________ ,which seemed (at the time) to fit well with how doctors assessed the impact of evidence on the diagnosis.
Rationality
Measure against an ideal concept of intelligence and a system does the "right thing" given what it knows.
microworlds
Minsky supervised a series of students who chose limited problems that appeared to require intelligence to solve. These limited domains became known as _____________
computational linguistics
Modem linguistics and AI, then, were "born" at about the same time, and grew up together, intersecting in a hybrid field called ____________________or natural language processing.
objective function
Modern control theory, especially the branch known as stochastic optimal control, has as its goal the design of systems that maximize an _________ over time.
induction
Principle which says that general rules are acquired by exposure to repeated associations between their elements.
Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally
Some definitions of artificial intelligence, organized into four categories
true
The fact that a program can find a solution in principle does not mean that the program contains any of the mechanisms needed to find it in practice.
logicist
The so-called ________ tradition within artificial intelligence hopes to build on such programs to create intelligent systems.
cognitive psychology
The view of the brain as an information-processing device
logic
These laws of thought were supposed to govern the operation of the mind; their study initiated the field called _______.
logical positivism
This doctrine holds that all knowledge can be characterized by logical theories connected, ultimately, to observation sentences that correspond to sensory inputs
Artificial Intelligence
This field attempts not just to understand but also to build intelligent entities
cognitive science
This interdisciplinary field brings together computer models from AI and experimental techniques from psychology to try to construct precise and testable theories of the workings of the human mind.
confirmation theory
This theory attempted to understand how knowledge can be acquired from experience
data mining
Using improved methodology and theoretical frameworks, the field arrived at an understanding in which neural nets can now be compared with corresponding techniques from statistics, pattern recognition, and machine learning, and the most promising technique can be applied to each application.
frames
assembling facts about particular object and event types and arranging the types into a large taxonomic hierarchy analogous to a biological taxonomy.
Decision theory
combines probability theory with utility theory, provides a for- mal and complete framework for decisions (economic or otherwise) made under uncertainty- that is, in cases where probabilistic descriptions appropriately capture the decision-maker's environment
Hebbian learning
demonstrated a simple updating rule for modifying the connection strengths between neurons
COGNITIVE SCIENCE
development of computer modeling led to the creation of the field of _____________
Euclid's algorithm for computing greatest common denominators.
first nontrivial algorithm
intractability
if the time required to solve instances of the problem grows exponentially with the size of the instances
game theory
included the surprising result that, for some games, a rational agent should act in a random fashion, or at least in a way that appears random to the adversaries.
satisficing
making decisions that are "good enough," rather than laboriously calculating an optimal decision-gave a better description of actual human behavior
weak methods
methods that do not scale up to large or difficult problem instances
connectionist models
models of intelligent systems were seen by some as direct competitors both to the symbolic models
Cybernetics
possibility of artificially intelligent machines
behaviorism
rejected any theory involving mental processes on the grounds that introspection could not provide reliable evidence.
incompleteness theorem
showed that in any language expressive enough to describe the properties of the natural numbers, there are true statements that are undecidable in the sense that their truth cannot be established by any algorithm.
convergence theorem
showing that his learning algorithm could adjust the connection strengths of a perceptron to match any input data, provided such a match existed.
neurons
the brain consisted of nerve cells or __________-
knowledge representation
the study of how to put knowledge into a form that a computer can reason with
Neuroscience
the study of the nervous system, particularly the brain
control theory
viewed purposive behavior as arising from a regulatory mechanism trying to minimize "error"-the difference between current state and goal state.
Bayesian network formalism
was invented to allow efficient representation of, and rigorous reasoning with, uncertain knowledge.