Machine learning is a branch out of research in artificial intelligence area. It is a field of study that gives computers the ability to learn with out being explicitly programmed.
Computer program is said to learn from experience E with respect to some task T and some performance measure P
and its performance on T measured by P improves with experience E.
Supervised learning
Given a data set and already knowing what our correct output should look like, meaning, having an idea that there is a relationship between the input and the output.
Mainly categories into regression and classification.
Regression
Predict results with in a continuous output,
meaning, trying to map input variables to some continuous function.
Predicting the price of the house based on size is an example for regression learning. Where price as a function of size is a continuous output, so it is a regression problem.
If the question is whether the house can be sold for more of less than the asking price, then it becomes classification problem as here we are classifying the houses based on price into two discrete categories. "More" or "Less"
Given the picture of a person, predict the age. here picture is an input variable for the person.
Classification
trying to predict results in a discrete output. trying to map input variables
into discrete categories.
Example: Given a patient with tumor we have to predict whether the tumor
is malignant or benign(non-malignant).
Unsupervised Learning
Allows us to approach problems with little or no idea what our results should like like. We can derive structure from data where we dont necessarily know the effect of the variables.
with unsupervised learning there is no feedback based on the prediction results.
By clustering the data based on relationships among the variables in the data, we can derive this structure.
Social network analysis
astronomical data analysis
market segmentation
organize computing clusters
Octave or Matlab tools are optimized for rapid vectorized calculations, which is very useful in maching learning. Apart from that
R, Python, Julia, Clojure tools are used in Maching leanring.
Clustering
Example: Take a collection of 1000000 different genes, and find a way to automatically group these into group that are somehow similar or related by different variables, such as lifespan, location, roles, and so on.
Non Clustering
Example: The cocktail party algorithm allows you to find structure in a chaotic environment (i.e. identifying individual voices and music from a mesh of sounds at a coctail party.)
Computer program is said to learn from experience E with respect to some task T and some performance measure P
and its performance on T measured by P improves with experience E.
Supervised learning
Given a data set and already knowing what our correct output should look like, meaning, having an idea that there is a relationship between the input and the output.
Mainly categories into regression and classification.
Regression
Predict results with in a continuous output,
meaning, trying to map input variables to some continuous function.
Predicting the price of the house based on size is an example for regression learning. Where price as a function of size is a continuous output, so it is a regression problem.
If the question is whether the house can be sold for more of less than the asking price, then it becomes classification problem as here we are classifying the houses based on price into two discrete categories. "More" or "Less"
Given the picture of a person, predict the age. here picture is an input variable for the person.
Classification
trying to predict results in a discrete output. trying to map input variables
into discrete categories.
Example: Given a patient with tumor we have to predict whether the tumor
is malignant or benign(non-malignant).
Unsupervised Learning
Allows us to approach problems with little or no idea what our results should like like. We can derive structure from data where we dont necessarily know the effect of the variables.
with unsupervised learning there is no feedback based on the prediction results.
By clustering the data based on relationships among the variables in the data, we can derive this structure.
Social network analysis
astronomical data analysis
market segmentation
organize computing clusters
Octave or Matlab tools are optimized for rapid vectorized calculations, which is very useful in maching learning. Apart from that
R, Python, Julia, Clojure tools are used in Maching leanring.
Clustering
Example: Take a collection of 1000000 different genes, and find a way to automatically group these into group that are somehow similar or related by different variables, such as lifespan, location, roles, and so on.
Non Clustering
Example: The cocktail party algorithm allows you to find structure in a chaotic environment (i.e. identifying individual voices and music from a mesh of sounds at a coctail party.)
No comments:
Post a Comment