What is Machine Learning ?
ML is an application/discipline of Artificial Intelligence, that provides system the ability to automatically learn and improve itself, without being explicitly programmed. And AI aims at making machine smarter by giving those capabilities to think on their own feet to make decisions or mimic human activities and one can think of ML as a subset of AI.
It focuses on the development of computer programs that can access data and use it to learn themselves. The learning process begins with observations of data, experience or instructions, this process helps to look for a pattern in data and make better decisions in the future.
Applications of ML :
Now a question arises, how does machine learning works ?
It comprises of different algorithms where it performs various amount of tasks by using input data. The more amount of data is fed to these algorithms, the more accurate the predicted data is.
When we get our output, we find out the accuracy of the algorithm according to the input data given.
Let's understand this with some example, suppose we want to predict the price of a new model of bike. So the steps will be like this:
Types of Machine Learning:
Below attached image is a brief overview on different types of machine learning along with some examples to improve the understanding behind them.
Now it can be understood by its name only, this learning works under some supervisor. In this learning, the training dataset contains both input data and the value we want to predict. And here the training data is labeled.
Examples of supervised learning are, naive bayes, gradient boosting.
This learning does not use output data. And it is mostly used to pre-process data, pre-train supervised learning algorithms. Examples are, PCA, LCA, K-Means. There is no labeled data.
It combines small amount of labelled data to large amount of unlabeled data during training. Applications of this learning includes, Content Classification, Speech Analysis.
It is the best way to earn the greatest reward. This learning follows various steps like the model (agent) will choose the action to maximize the reward based on what kind of environment we are choosing to implement. These actions will change the state of the model and environment. They may be interpreted to reward the model. By performing this in loop, the behavior of the model will be improved automatically and the accuracy of our model will surely show some improvement.
This kind of learning performs better on dynamic systems.
Now remember, this article contains only the introductory part, you will learn about these algorithms properly in upcoming articles.
Till then, keep learning !