Machine Learning
Machine Learning is a subset of
Artificial Intelligence.It is the field of studying scientifically the various ways to give a machine the ability to perform certain operations, though it may not have been explicitly programmed to do so.The machine takes in inputs from surroundings uses certain kinds of algorithms to generate an output based on logical and mathematical calculations and perform accordingly.
 |
| Machine Learning to Play Piano |
Types of Machine Learning
There are three types of learning in Machine Learning :-
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
Supervised Learning
In supervised Learning yo have an input variable X and an output variable Y.To understand this consider an example suppose you wanted to train a robot to differentiate a male face and a female face,you will use the supervised learning criteria to train it.At first you will give the robot labelled data in raw form which can include lots and lots of pictures of man and women labelled s 'Man' and'Women'.The robot uses certain kinds of algorithm, processes it and builds a model that is trained.It then takes input data from its surroundings processes it performs certain calculations based on the algorithms used to train it, and gives output as Man or Women.
 |
| Supervised Learning: a model used in Machine Learning |
Supervised Learning Algorithms
- Linear Regression
- Logistic Regression
- Decision Tree
- Random Forest
- KNN
- Naive Bayes Classifier
Here is a very short and informal definations of Machine Learning Algorithms
Linear Regression
Linear Regression is used to predict the value of a dependent variable Y with the help of an independent variable Y.
 |
| Linear Regression: A Machine Learning Approach |
Logistic Regression
Logistic Regression is a statistical method for analysing a dataset in which there are one or more independent variables that determine an outcome which needs to be predicted.Logistics Regression produces the result in a binary format.
 |
| Logistic Regression: Another Machine Learning Approach |
Decision Tree
A decision Tree is one which has a tree like structure and its internal node represents test on an attribute.Each branch represents an outcome of the test and each leaf node represents the class label.
 |
| Decision Tree used in Machine Learning |
Random Forest
Random Forest is an ensemble classifier made using different decision trees.In this model we use trees to reduce the risk of overfitting. It produces highly accurate outcomes for large data. It operates by constructing decision trees during training phase. The decision of the the majority of trees is chosen by the Random Forest as the final Decision.
 |
| Random Forest: A combination of Decision Trees to provide the best output in Machine Learning |
KNN Algorithm
K Nearest Neighbour is a simple algorithm that stores all the available cases and classifies the new data or case based on similarity measure.
 |
| KNN Algorithm used in Machine Learning |
Naive Bayes Classifier
Naive Bayes Classifier is based on Baye's Theorem which gives the conditional probability of an event A given B.
 |
| Bayes Theorem used in Naive Bayes Classifier |
Unsupervised Learning
In Unsupervised Learning the data given to the machine is unlabelled.To understand this consider teaching the machine to differentiate between baseballs basketballs and footballs, to do so you would first give the machine, the data which has pictures of baseballs, basketballs and footballs.
The Unsupervised Model would take the data uses its algorithm and processes it to give output that is 'unlabelled'.
 |
| Unsupervised Learning |
Reinforcement Learning
Reinforcement Learning is one in which an agent or our machine learns how to act in an environment by performing actions in order to get maximum reward. It is more likely based on how we humans think and act.
 |
| Reinforcement Learning |
Comments
Post a Comment