In the last section we have got an idea about unsupervised learning. To make the concept clear, let’s see a unsupervised learning example.
Unsupervised learning helps us to figure out why the dataset is special. Suppose we have different types of cats and different types of dogs.
Therefore, there are many data points that are similar in nature.
Based on this, we can group them by similarity. The unsupervised learning algorithm can cluster cats on one side and dogs on the other.
As a result, unsupervised learning algorithms determine the data patterns on its own.
It keeps cats on one side and dogs on the other.
If you are a complete beginner your journey to learn TensorFlow might start from here.
For the TensorFlow beginners we have a dedicated category – TensorFlow for Beginners.
But besides that, you may need to learn several other machine learning and data science libraries.
As a result, you may check these categories as well – NumPy, Pandas, Matplotlib.
However, without learning Python, you cannot learn the usages of these libraries. Why? Because they all use Python as the Programming language.
Therefore please learn Python at the very beginning and start learning TensorFlow.
And, finally please check our Mathematics, Discrete Mathematics and Data Structures categories specially. We have tried to discuss from basic to intermediate level so that you can pick up the core ideas of TensorFlow.
It happens because of the correlation of data points.
As we said before, human cognition is in-built, so it can figure out the same objects just by observing the similarities.
As an unsupervised learning example we can think of some documents where a certain topic appears again and again.
This recurring pattern makes up the data. Otherwise the documents have no correlation.
Let’s be more specific.
In every document somehow or other the theme ‘famine’ occurs or it refers to ‘hollywood’ and things like that.
The same way, you can find some recommendation systems in E-Commerce applications.
Here the unsupervised learning algorithms work on your buying habits.
As an outcome it decides which cluster of customers you belong to. Because your buying habits have put you in the same group that usually buy crime thrillers.
Learning from this experience the algorithm knows your preferences and suggests books.
Finally we will give an instance of an unsupervised learning algorithm. This example is quite common and we know that.
For some time we have been talking about similarities or finding similar patterns. Right?
Suppose we are uploading photos to our social media accounts.
It is quite likely that some faces will appear several times.
Clustering algorithms which belong to unsupervised learning try to partition the same faces in a distinct collection.
It actually tries to help you to reorganize the photos in a better way.
Certainly the social media application does not care about the emotional parts.
A face may have appeared in many photos but that does not necessarily mean you wanted to organize the photos in the same way.
Leave a Reply