Classification
Classification is used to determine what category something belongs in, after seeing a number of examples of values from several categories.
A good example of a classification task is Sentiment Analysis e.g. determining wheter a reaction or consumer review of a product is positive or negative.
In order to create automated classification methods either models or Machine Learning techniques are utilized.
Prediction
In prediction, first the input is analysed in order to predict an output value.
This is achieved by (statistical) modeling that is done either by an expert human modeller or utilizing Machine Learning techniques.
A good example of predictive tasks is Stock Market Prediction: based
on several input parameters a stock price value is predicted. Many other applications in which continous values and value ranges need to be predicted based on the past data are made possible by prediction in AI.
Sensing
In Artificial Intelligence, sensing is the ability of computing machines to sense and interpret images, sounds, or other contents of their environments, or of the contents of stored media. Real-time perception of a machine's environment is useful in industrial processes, such as assembly, inspection, diagnosis, vehicle guidance, etc. Off-line perception of stored media is useful in medical and aerial photo interpretation, content-based indexing and retrieval of movies and images, etc.
Machine perception includes
- Computer vision
- Machine hearing
- Machine touch