The basic principle behind machine learning is the automated analysis of huge amount of data. In simple words we can define machine learning as a set of methods that can automatically detect patterns in data
and then use the uncovered patterns to predict future data, or to perform other kinds of decision such as how to collect more data. In order to be an expert in machine one needs to know the entire probability theory,
which is the very concept of machine learning as it deals with predicting patterns.
Machine learning is divided into three categories:
1) supervised learning
2) unsupervised learning
3) reinforcement learning
In supervised learning computer is provided with input and output examples and the goal is to map the input and the output. The input data is called is called training data and has a known label such as spam/not spam.
A model is prepared through a training process which makes predictions. If the predictions go wrong the model is corrected until it acquires a desired level of accuracy.
In Unsupervised learning no labels are provided to the model and it is left on its own to make predictions. Unsupervised learning can help us to discover hidden patterns in the data. So how does this type of learning works?
A model is prepared by simplifying the structures present in the input data. This helps us to extract general rules and the mathematical processes in the data which ultimately which helps us to find similar patterns in the data.
In reinforcement learning the model interacts with a dynamic environment and it must perform certain task to achieve its goals without anyone instructing it. Best example is driving a vehicle.
Therefore, in this type of learning the model must learn structures to organize the data as well as make predictions.
some applications of Machine Learning are:-
Face detection: Cameras can automatically detect a person in a photo when the person smiles more accurately this is dur to the advances in machine learning algorithms.
Face recognition: This is where a computer program can identify an individual from a photo.
Weather forecast: Machine learning is applied in weather forecasting software to improve the quality of the forecast.
For more information on Machine learning click the following links:-https://www.cs.ubc.ca/~murphyk/MLbook/pml-intro-22may12.pdf
some of the questions that came to my mind while I was doing the research are:-
Q.1)What are the mathematical concepts other than probablity that are used in Machine learning?
Q.2)how does reinforcement learning works without any guidance from an user?
Q.3)What is the scope of Machine Learning in the furure?
sources:- wikipedia,Machine Learning Kevin P. Murphy