Machine learning Note 1--introduction

Introductionwhat is machine learning?

The definitions of machine learning is offered. Arthur Samuel described it as: "The field of study that gives computers the ability to learn without being explicitly prog Rammed. " This was an older, informal definition.

Tom Mitchell provides a more modern definition: "A computer program was said to learn from experience E with respect to SOM E Class of tasks T and performance measure p, if its performance at the tasks in T, as measured by P, improves with experience E. "

Example:playing Checkers.

• E = The experience of playing many games of checkers
• T = The task of playing checkers.
• P = The probability that the program would win the next game.

Supervised learning

In supervised learning, we is given a data set and already know what we correct output should That there is a relationship between the input and the output.

Supervised learning problems is categorized into "regression " and "classification" problems. In a regressionproblem, we is trying to predict results within a continuous output, meaning this we are Trying to map input variables to some continuous function. In a classification problem, we is instead trying to predict results in adiscrete output. In the other words, we is trying to map input variables into discrete categories.

Example:

Given data about the size of houses in the real estate market, try to predict their price. Price as a function of the size is a continuous output, so the is a regression problem.

We could turn this example to a classification problem by instead making our output on whether the house ' sells for M Ore or less than the asking. " Here we is classifying the houses based on price into the discretecategories.

Unsupervised learning

Unsupervised learning, on the other hand, allows us to approach problems with little or no idea what we results should lo Ok like. We can derive structure from data where we don ' t necessarily know the effect of the variables.

We can derive this structure by clustering The data based on relationships among the variables in the data.

With unsupervised learning there are no feedback based on the prediction results, i.e., there are no teacher to correct. It ' s not just about clustering. For example, the associative memory is unsupervised learning.

Example:

Clustering: Take a collection of $ essays written on the US Economy, and find a-to-automatically group the SE Essays into a small number that is somehow similar or related by different variables, such as word frequency, sentence Length, page count, and so on.

associative: Suppose a doctor over years of experience forms associations in he mind between patient characteris Tics and illnesses that they has. If A new patient shows up then based on the patient ' s characteristics such as symptoms, family medical history, physical attributes, mental outlook, etc The Doctor Associates possible illness or illnesses based on what the doctor have seen BEFO Re with similar patients. The same as rule based reasoning as in expert systems. In this case we would like to estimate a mapping function from patient characteristics into illnesses.

Machine learning Note 1--introduction