Unsupervised Learning
Unsupervised Learning:
An Unsupervised Learning is where the Machine learns by itself when provided with a data with same kind of labels.
The below image is an example of Supervised learning where the Labels (O & X) are clearly specified given 2 Features/Attributes. The distinguishing factor is clearly slated and the Machine is asked to learn it.
But in the case of Unsupervised learning, the dataset that is provided doesn't have a distinguished label and the Machine is asked to make some sense of it.
The Machine tries to understand the data and makes some sense of it by Clustering them together that lie nearby as below. This is a clear example of Clustering, where closely related labels are grouped together.
A very good example of Clustering Problem is Google News. The closely related news are grouped together so that the Users can read all the news that relate to it. Below we can find the news related to BP Oil firm.
Q&A by Andrew Ng:
Unsupervised learning allows us to approach problems with little or no idea what our results should look 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 is no feedback based on the prediction results.
An Unsupervised Learning is where the Machine learns by itself when provided with a data with same kind of labels.
The below image is an example of Supervised learning where the Labels (O & X) are clearly specified given 2 Features/Attributes. The distinguishing factor is clearly slated and the Machine is asked to learn it.
But in the case of Unsupervised learning, the dataset that is provided doesn't have a distinguished label and the Machine is asked to make some sense of it.
The Machine tries to understand the data and makes some sense of it by Clustering them together that lie nearby as below. This is a clear example of Clustering, where closely related labels are grouped together.
A very good example of Clustering Problem is Google News. The closely related news are grouped together so that the Users can read all the news that relate to it. Below we can find the news related to BP Oil firm.
Q&A by Andrew Ng:
Unsupervised learning allows us to approach problems with little or no idea what our results should look 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 is no feedback based on the prediction results.
Comments
Post a Comment