AI Terms and definitions

Define Dijkstra's Algorithm

Is a method of finding the shortest path
between two points in a graph. It is the
basis of technology such as GPS tracking, therefore,making it an important part of AI.

1 of 22

Define A* Algorithm

The A* algorithm is based on Dijkstra, but adds an extra heuristic (h) value, this is provides an estimate on how far it takes to get from the source to its destination, it uses the principles of taking the shortest route to the destination (smart routing

2 of 22

Define AI

This means artificial Intelligence, it is the simulation/replication of human actions and intelligence performed by machines like computers and robots

3 of 22

Define Narrow AI

This is when a machine has a superior performance to a human in one specific task

4 of 22

Define General AI

This is when a machine has a similar performance to a human in any intellectual task

5 of 22

Define Strong AI

This is when a machine has a superior performance to a human in many tasks

6 of 22

Define Node/Vertex in terms of Dijkstra's algorithm

This refers to each point on the graph

7 of 22

Define Final Value in terms of Dijkstra's algorithm

This refers to the total distance traveled to reach each node, starting from the start node. The smallest value will always be used.

8 of 22

Define Working Value in terms of Dijkstra's algorithm

This refers to the current distance that was travelled from one node to another (this is the value before all the paths have been taken, as the value may become smaller if a shorter path was found after all the paths were explored)

9 of 22

Define Machine Learning

This is a subset of AI, where the algorithms are trained by learning from past experiences and mistakes. These systems may even be able to make future predictions based on past data, like an increase in profits in the next year based on the last 20 years

10 of 22

Define Labelled Data

Data that is defined and recognizable

11 of 22

Define Unlabelled Data

Data that may be incomplete and not as easily recognizable as labelled data

12 of 22

Define Supervised Learning

System that makes use of recognition analysis and classification analysis. It’s used to predict future outcomes based on past data. It requires both an input and an output to be given to the model so it can be trained

13 of 22

Define Unsupervised Learning

System which is able to identify hidden patterns from the input data provided; they are not trained using the correct answer

14 of 22

Define Reinforcement learning

The system is not trained. It learns on the basis of ‘reward and punishment’ when carrying out an action

15 of 22

Define Reward and Punishment principle in terms of reinforcement learning

This is the basis by which the system learns, this is typically used in search engines, where a result that is given will be classed as a success if the user does not browse past the first page (Reward) and flagged as a fail when the user goes to the seco

16 of 22

Define Semi-supervised learning (active)

This makes use of labelled and unlabelled data to train algorithms that can interactively query the source data and produce a desired output.

17 of 22

Define Deep Learning

A subset of machine learning, which is a neural network with three or more layers.

18 of 22

Define Text Mining

It is the process of converting unstructured text into a structured format to identify patterns and generate new insights in the data

19 of 22

Define Computer Assisted Translation

CAT for short hand form, it is the use of software in order to, assist the human translator during the translation process, this could be during the translation of files, documents, recordings etc...

20 of 22

Define Chatbot

These interact through instant messaging, and by artificially replicating patterns of human
interactions using machine learning principles.

21 of 22

Define Backpropagation

This is an algorithm that is designed to test for errors, while working back from the output nodes to the input nodes (backtracking/retracing steps taken in the algorithm)

22 of 22

Get Revising

AI Terms and definitions

Other cards in this set

Card 2

Front

Back

Card 3

Front

Back

Card 4

Front

Back

Card 5

Front

Back

Comments

Similar Computing resources:

Other cards in this set

Card 2

Front

Back

Card 3

Front

Back

Card 4

Front

Back

Card 5

Front

Back

Comments

Related discussions on The Student Room

Similar Computing resources: