Artificial Intelligence in Computer Science, Study Guides, Projects, Research of Computer Science

An overview of artificial intelligence (AI) in computer science. It covers the definition of AI, desirable traits of AI, the Turing Test, artificial neural networks, back propagation algorithm, decision trees, state-space, brute force approach, and swarm intelligence model. The document also discusses the characteristic of human reasoning and how AI specialists try to get computers to emulate this characteristic. It is a useful resource for students studying computer science and AI.

Typology: Study Guides, Projects, Research

2023/2024

Available from 02/04/2024

star_score_grades
star_score_grades 🇺🇸

3.7

(21)

1.6K documents

1 / 4

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
COSC Computer Science: Chapter 15
Artificial Intelligence
Artificial intelligence (AI) - correct answer - The intelligence of machines and the branch of
computer science that aims to create it
- The study and design of intelligent agents (as system that perceives its environment and takes
actions that maximize its chances of success)
Turing's theory of computation - correct answer a machine, by shuffling symbols could simulate
any conceivable act of mathematical deduction.
We need not decide if a machine can think. We need only decide if a machine can act as
intelligently as a human being
Desirable Traits of AI - correct answer • Deduction, reasoning, problem-solving • Knowledge
representation • Planning • Learning • Natural language processing • Motion and manipulation
• Perception • Social intelligence • Creativity • General intelligence
The Turing Test - correct answer 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.
Can you tell if you are interrogating a machine or a human?
Artificial neural networks - correct answer Can be created by simulating individual neurons in
hardware and connecting them in a massively parallel network of simple devices
Neural network - correct answer - Can learn from experience by modifying the weights on its
connections
- Can be given an initial set of weights and thresholds that is simply a first guess
- Network is then presented with training data
pf3
pf4

Partial preview of the text

Download Artificial Intelligence in Computer Science and more Study Guides, Projects, Research Computer Science in PDF only on Docsity!

COSC Computer Science: Chapter 15

Artificial Intelligence

Artificial intelligence (AI) - correct answer - The intelligence of machines and the branch of computer science that aims to create it

  • The study and design of intelligent agents (as system that perceives its environment and takes actions that maximize its chances of success) Turing's theory of computation - correct answer a machine, by shuffling symbols could simulate any conceivable act of mathematical deduction. We need not decide if a machine can think. We need only decide if a machine can act as intelligently as a human being Desirable Traits of AI - correct answer • Deduction, reasoning, problem-solving • Knowledge representation • Planning • Learning • Natural language processing • Motion and manipulation
  • Perception • Social intelligence • Creativity • General intelligence The Turing Test - correct answer 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. Can you tell if you are interrogating a machine or a human? Artificial neural networks - correct answer Can be created by simulating individual neurons in hardware and connecting them in a massively parallel network of simple devices Neural network - correct answer - Can learn from experience by modifying the weights on its connections
  • Can be given an initial set of weights and thresholds that is simply a first guess
  • Network is then presented with training data

Back propagation algorithm - correct answer Eventually causes the network to settle into a stable state where it can correctly respond to all inputs in the training set Characteristic of human reasoning - correct answer Ability to draw on a large body of facts and past experience to come to a conclusion Artificial intelligence specialists try to get computers to emulate this characteristic Decision tree for a search algorithm - correct answer Illustrates the possible next choices of items to search if the current item is not the target Decision tree for sequential search is linear Know what the difference decision trees are like. Linear/Sequential is easy because it only has one choice each time. Binary is harder because 2 each time so more branches State-Space is the worst because of Exponential Growth Solution path - correct answer Takes us from the initial state to a winning configuration, and the graph nodes along the way represent the intermediate configurations Brute force approach - correct answer Traces all branches of the state-space graph Swarm intelligence model - correct answer - Uses simple agents that:

  • Operate independently
  • Can sense certain aspects of their environment
  • Can change their environment Models the behavior of a colony of ants

Reactive strategy: Robotics - correct answer uses heuristic algorithms to allow the robot to respond directly to stimuli from its environment heuristic algorithms - correct answer The term heuristic is used for algorithms which find solutions among all possible ones ,but they do not guarantee that the best will be found,therefore they may be considered as approximately and not accurate algorithms.These algorithms,usually find a solution close to the best one and they find it fast and easily. Categories of tasks for AI - correct answer Computational, recognition, and reasoning