The document discusses well-posed learning problems, defining them as scenarios where a computer program improves its performance on a task through experience. It outlines the necessary traits of such problems: a defined task, a performance measure, and experience. Examples include email spam filtering, checkers, handwriting recognition, robot driving, fruit prediction, face recognition, and automatic translation.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
0 ratings0% found this document useful (0 votes)
4 views2 pages
Module1_Lecture2
The document discusses well-posed learning problems, defining them as scenarios where a computer program improves its performance on a task through experience. It outlines the necessary traits of such problems: a defined task, a performance measure, and experience. Examples include email spam filtering, checkers, handwriting recognition, robot driving, fruit prediction, face recognition, and automatic translation.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 2
LEARNING PROBLEMS AND SCENARIOS
Well Pose learning problem
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. That means, Leaning=Improving with Experience at some Task -Improve over task T -With respect to performance measure, P -Based on Experience, E Any problem can be segregated as well-posed learning problem if it has three traits – -Task -Performance Measure -Experience Well Pose learning problem Examples To better filter emails as spam or not A checkers learning problem Handwriting Recognition Problem A Robot Driving Problem Fruit Prediction Problem Face Recognition Problem Automatic Translation of documents Well Pose learning problem – Scenarios Problem Statement Task (T) Performance (P) Experience (E) 1.To better filter Classifying emails as The fraction of Observing you label emails as spam or spam or not emails accurately emails as spam or not classified as spam or not spam not spam 2.Playing checkers Playing against Make perfect moves It plays itself to learning opponents to win to win games improve game 3. Handwriting Acknowledging percent of words a directory of Recognition handwritten words accurately classified handwritten words Problem within portrayal with given classifications 4. A Robot Driving Drive the car in a 4- Source to destination order of images and Problem lane highway the average distance steering instructions travelled noted down while observing a human driver 5. Fruit Prediction forecasting different able to predict training machine Problem fruits for recognition maximum variety of with the largest fruits datasets of fruits images 6. Face Recognition predicting different able to predict training machine Problem types of faces maximum types of with maximum faces number of datasets of different face images 7. Automatic translating one type able to convert one training machine Translation of of language used in a language to other with a large dataset documents document to other efficiently of different types of language languages