Intro to Comp Sci Chapter 13

Artificial intelligence

The study of computer systems that attempt to model and apply the intelligence of the human mind (ex: writing a program to pick out objects in a picture)

Alan Turing

An English mathematician who wrote a landmark paper in 1950 that asked the question: Can machines think?

He proposed a test to answer the question “How will we know when we’ve succeeded?”

Turing Test

A test to empirically (by means of observation or experience rather than theory or pure logic) determine whether a computer has achieved intelligence.

a human interrogator must determine which respondent is the computer and which is the human (A or B); procedure is repeated with numerous human interrogators and premise is that if it could fool enough interrogators, then it could be considered intelligent

Weak Equivalence

two systems (human and computer) are equivalent in results (output), but they do not arrive at those results in the same way

Strong equivalence

two systems (human and computer) use the same internal processes to produce same result

Hugh Loebner

New York philanthropist organized 1st formal instantiation of the Turing test; competition since 1991; grand prize of $100,000 and a solid gold medal will be awarded for the first computer whose responses are indistinguishable from a human’s (including text, visual, and audio input)

Loebner Prize

the first formal instantiation of the Turing test, held annually

Chatbots

a program designed to carry on a conversation with a human user

Knowledge representation

techniques used to represent knowledge so that a computer system can apply it to the intelligent problem solving

Expert System

computer systems that embody the knowledge of human experts

Neural networks

computer systems that mimic the processing of the human brain

Natural-language processing

the challenge of processing languages that human use to communicate

Robotics

the study of robots

Semantic networks and Search trees

promising techniques for representing knowledge

Semantic network

a knowledge representation technique that focuses on the relationships between objects

directed graph

used to represent a semantic network

nodes

represent objects

arrows

represent relationships; indicate the types of relationships

Inheritance relationship

indicates that one object is-a more specified version of another object

Instantiation

the relationship between an actual object and something that describes it (like a class)

search trees

Structure that represents all possible moves in a game, for both you and your opponent; represent a series of decisions made by the players.

pruning

eliminating path that no human player would consider reasonable

depth-first

A technique that involves analyzing selective paths all the way down the tree that we hope we will result in successful moves / searching down the paths of a tree prior to searching across levels

breadth-first

A technique that involves analyzing all possible paths but for only a short distance down the tree, which tends to yield the best results / searching across levels of a tree prior to searching down specific paths

network design

The objects in the network represent the objects in the real world; the relationships that we represent are based on the real-world questions that we would like to ask; the types of relationships represented determine which questions are easily answered, which are more difficult to answer, and which cannot be answered

Knowledge-based system

Software that uses a specific set of information (organized data), from which it extracts and processes particular pieces

expert system

A software system based on the knowledge of human expert

A rule-based system

a software system based on a set of if-then rules; set of rules in an expert system is referred to as its knowledge base

An inference engine

the software that processes rules to draw conclusions / determines how rules are followed

Executing Inference engine

System will ask user questions and based on users responses, it will determine which course of action will be recommended to user

Advantages of expert system

1. Goal oriented: it doesn’t focus on abstract or theoretical information but rather focuses on solving a specific problem. 

2. Efficient: It records previous responses and doesn't ask irrelevant questions.

3. can usually provide useful guidance even if you don't know the answer to some questions.

Artificial Neural Network

A computer representation of the knowledge that attempts to mimic the neural networks of the human body

neuron

a single cell that conducts a chemically based electronic signal; at any point in time, a neuron is in either an excited state or an inhibited state

Excited State

Neuron conducts a strong signal

Inhibited State

neuron conducts weak signal

natural language processing

the challenge of processing languages that human use to communicate

3 basic types of processing occur during human/computer voice interaction

voice synthesis, dynamic voice generation, phonemes

Voice Synthesis

using a computer to recreate the sound of human speech

Dynamic Voice Generation

a computer examines the letters that make up a word and produces the sequence of sounds that correspond to those letters in an attempt to vocalize the word

Phonemes

the sound units into which human speech has been categorized; the way dynamic voice generation is completed

Voice Recognition

using a computer to recognize the words spoken by a human

Recorded speech

a large collection of words is recorded digitally, and individual words are selected to make up a message (ex: Siri, Alexa)

Problems with understanding speech

• Each person’s sounds are unique

• Each person’s sphere of mouth, tongue, throat, and nasal cavities that affect the pitch and resonance of our spoken voice are unique

• Speech impediments, mumbling, volume, regional accents, and the health of the speaker are further complications

• Humans speak in a continuous, flowing manner, stringing words together

• Sound-alike phrases like “ice cream” and “I scream”

• Homonyms such as “I” & “eye” or “see” & “sea”

Voiceprint

the plot of frequency changes over time representing the sound of the human speech

Natural-Language Comprehension

using a computer to apply a meaningful interpretation to human communication

Lexical ambiguity

the ambiguity created when words have multiple meanings

Syntactic ambiguity

the ambiguity created when sentences can be constructed in various ways

Referential Ambiguity

the ambiguity created when pronouns could be applied to multiple objects

mobile robotics

The study of robots that move relatively to their environment while exhibiting a degree of autonomy (the right or condition of self-government)

Sense-Plan Act (SPA) Paradigm

The world of the robot is represented in a complex semantic net in which the sensors on the robot are used to capture the data to build up the net

Subsumption Architecture

Rather than trying to model the entire world all the time, the robot is given a simple set of behaviors, each associated with the part of the world necessary for that behavior

3 Laws of Robotics by Isaac Asimov

1. A robot may not injure a human being, or through inaction, allow a human being to come to harm.

2. A robot must obey orders given to it by a human being.

3. A robot must protect its own existence.