What is Machine Learning ?

What is actually ML ?

• We can call it as a sub-filed of Artificial Intelligence.
• It is basically about predict future. Think like you have a bunch of raw data. Through ML we can create a model which will identify patterns that exist on those data. So when a new data set is entered, the created model will be able to recognize those patterns and predict the future.
• There are multiple applications of ML, such as detecting credit card fraud, Determining whether a customer likely switches to a competitor. (Customer churn / loss of clients or customers), NLP (Natural language processing) , Computer vision, including object recognition, Robot locomotion , Sentiment analysis, Speech & handwriting recognition, Stock market analysis, Deciding when to do a maintenance on a factory robot.
• Simply we can describe the process as                                                     A bunch of data --> Identify Patterns --> Create a model (Ability to recognize patterns) --> Predict Future
• This process is iterative and should be periodically repeated if you want to get a good model.
• Deep Blue is the first ever chess-playing computer developed by IBM, which I found interesting when it's come to real-world AI . AlphaGo is another fascinating example , which is able to play the board game Go. Nowadays the big topic is Tesla,(electric vehicles manufacturers). They use ML for the auto pilot mode in Tesla model 2/3.
• There are plenty of open source libraries we can use to implement machine learning, such as scikit learning and Tenserflow.
• Machine learning is the study of algorithms that learn from examples and experience.

What is a Classifier ?

• We can call it as a function , it takes some data as input and assigns a label to it as output. Create a classifier by finding patterns in example is called Supervised Learning.Simply supervised learning is the technique to write classifier automatically.