Machine Learning

 What is machine learning? 

Machine Learning is an application of artificial intelligence where a computer/machine learns from the  input data and makes future predictions. The performance of such a system should be at least human level. In order to perform the task system learns the data-set provided.

Machine learning generally categories into three category

1. Supervised machine learning.

2. Unsupervised machine learning.

3. Reinforcement learning.

 

Now we will learn about the each type of machine learning one by one.

1. Supervised Machine Learning: Supervised machine learning is the type of machine learning in which machines are trained using well labelled data set and on the basis of that data machine predict the output.

Data set here is categorized one.

In real scenario supervised machine learning can be used for risk assessment, fraud detection, image clarification, spam detecting etc.  

KNN is the example of supervised classification algorithm.

2.  Unsupervised machine learning : unsupervised machine learning is the type of algorithm that learns that learns pattern from untagged data. Here models are trained using unlabeled data set are allowed to act on that data without any supervision. 

In supervised machine learning data is is not categorized. 

K means clustering is an unsupervised clustering algorithm.

3. Reinforcement learning: Reinforcement learning is a machine learning training method based on rewarding desired behaviors and/or punishing undesired ones. In general a reinforcement agent can learn its environment and can take action through trial and error.

How does supervised machine learning work ?

Supervised machine learning requires the data scientist to train the data with both labeled inputs and desired outputs . Supervised machine learning is good for the mention tasks:

• Binary Classification: In this we divide the data into two categories.
• Multi- Class Classification: Choosing between more than two types of answers.
• Regression modeling: Predicting continuous values. 

How does unsupervised machine learning work?

Unsupervised machine learning algorithm do not requires data to be labeled. They sift through unlabeled data to look for patterns that can be used to group data points into subsets, Most types of deep cleaning, including neural networks are supervised algorithm.

Unsupervised machine learning is good for the following tasks

• Clustering : Splitting the datasets into groups based on similarity