Introduction to Machine Learning
Supervised, Unsupervised & Reinforcement….
Hello world, i hope you are all doing well. In this post we will learn about Machine learning concepts.
As many of us know Machine Learning(ML) is subset of Artificial Intelligence(AI). The objective of ML is to enable machines to learn by themselves using the provided data and make accurate predictions or we can say that it is a method to train the ML algorithms such that they can learn how to make correct predictions.
The fundamental goal of ML is to find the pattern in existing data. That means we feed the data to Machine and we ask “hey these are data, now your task is to learn and find it out the pattern in data”. If you observe what i am trying to say is we are not doing any code to find pattern, we are just feeding the data and we are expecting from machine to provide some kind of insight in data. So, the machine learning is all about to learn from the data without doing any explicit instructions.
Machine Learning Algorithm depends on the data. If we feed more data algorithm output will be more accurate. As we know data in our world increasing everyday drastically and Machine Learning algorithm work more effectively and accurately.
Machine Learning VS Statistical
Most of us having doubts between Machine learning and Statistics models.
Briefly we can say that -
- Machine learning is an algorithm or tool that can learn from data without relying on the rule-based programming. As i said ML is sub-field of Artificial intelligence. ML is all about predictions, supervised learning, unsupervised learning etc.
- Statistics modeling gives the clarification of relationships between variables in the data set.Statistics is sub-filed of mathematics. Statistics is about sample, population, hypothesis etc.
Machine Learning Algorithms
Broadly, there are three types of Machine Learning Algorithms-
Supervised Machine Learning -
In Supervised learning, we have given the set of data and we already known that what our correct output should look like, having the idea that there is a relationship between input/independent variable and output/dependent variable. In other words, we have prior knowledge of what our output/dependent variables values would be. Example — predict price of house, someone will win the election or not(yes or no) etc.
Supervised learning problems categorized into two types-
- Regression- In regression problem we are trying to predict results within a continuous(to know more about continuous) output or trying to map the input variables to some continuous function. Examples — predict the price of house,predict stock market price
- Classification- In classification problem we are trying to predict results within a discrete or trying to map the input variables to some discrete categories. Example — classify whether a patient has decease or not,classify whether a email spam or not.
Unsupervised Machine Learning -
In Unsupervised learning, it allows us to approach problems with little or no idea what our results should look like. We can derive structure from data where we don’t necessarily know the effect of the variables.
Unsupervised learning types-
- Clustering- It is a method to grouping a set of objects that are similar to other objects in the same cluster and dissimilar data points to other cluster. In cluster the data is unlabeled and the process is unsupervised. Sometimes we get confused with classification and clustering, no need to get confused only remember a classification algorithm predict the labeled data and a clustering algorithm deals with unlabeled to group the objects that are similar is characteristics. Example — grouping customers by purchasing behavior.
- Association- It s a popular and well researched method for discovering interesting relations between variables in large databases. It is intended to identify strong rules discovered in databases using different measures of interestingness. Example — If people will buy product a will buy product b.
Reinforcement Learning-
Reinforcement learning is all about making decisions sequentially. In simple words we can say that the output depends on the state of the current input and the next input depends on the output of the previous input. It also known as semi-supervised learning model.
Summary-
In this post we covered the basics of machine learning, type of machine learning, Supervised, Unsupervised & Reinforcement learning and their types like Regression, Classification, Clustering & Association. In my upcoming i will explain all kind of algorithm like Linear regression, Logistic regression, KNN, k-means etc. with real time examples. Stay tuned…… :)
If you think this post helped you in any way just hit the clap and yeah most important to follow me .. Enjoy Machine learning.. :)
