Well posed learning problems
Well Posed Learning Problem β A computer program is said to learn from experience E in context to some task T and some performance measure P, if its performance on T, as was measured by P, upgrades with experience E.
Any problem can be segregated as well-posed learning problem if it has three traits β
- Task
- Performance Measure
- Experience
Certain examples that efficiently defines the well-posed learning problem are β
1. To better filter emails as spam or not
- Task β Classifying emails as spam or not
- Performance Measure β The fraction of emails accurately classified as spam or not spam
- Experience β Observing you label emails as spam or not spam
2. A checkers learning problem
- Task β Playing checkers game
- Performance Measure β percent of games won against opposer
- Experience β playing implementation games against itself
3. Handwriting Recognition Problem
- Task β Acknowledging handwritten words within portrayal
- Performance Measure β percent of words accurately classified
- Experience β a directory of handwritten words with given classifications
4. A Robot Driving Problem
- Task β driving on public four-lane highways using sight scanners
- Performance Measure β average distance progressed before a fallacy
- Experience β order of images and steering instructions noted down while observing a human driver
5. Fruit Prediction Problem
- Task β forecasting different fruits for recognition
- Performance Measure β able to predict maximum variety of fruits
- Experience β training machine with the largest datasets of fruits images
6. Face Recognition Problem
- Task β predicting different types of faces
- Performance Measure β able to predict maximum types of faces
- Experience β training machine with maximum amount of datasets of different face images
7. Automatic Translation of documents
- Task β translating one type of language used in a document to other language
- Performance Measure β able to convert one language to other efficiently
- Experience β training machine with a large dataset of different types of languages
Contact Us