MACHINE LEARNING

Machine learning(ML) is a subset of Artificial Intelligence.

ML enables computers to learn from data and make decisions or predictions without being explicitly programmed to do so.

Revolves around creating and implementing algorithms to facilitate these decisions and predictions.

Machine learning can be generally categorized into three types.

This solely based on the nature of the learning system and the data available.

• Supervised Learning

• Unsupervised Learning

• Reinforcement Learning

This blog specifically delves into basic aspects of supervised V unsupervised machine learning as well as the key differences

SUPERVISED MACHINE LEARNING

This is a type of machine learning that learns the relationship between the input and the output.

Defined by its use of labelled data

1. Input : Better known as features or the x-variables
2. Output : Referred to as the target or y-variables

Labelled data is the type of data that contains both the features and target/ Dataset that contains a lot of examples of features and target

Labelled data is the key difference between supervised and unsupervised ML

The process of learning the relationship of features and target from the dataset is identified as Training or Fitting

CLASSIFICATION

Here algorithms learn from the data to predict an outcome or event in the future,

In a bank scenario whereby they would like to know if a customer will default on a loan. The historical data on the said customer will entail.

• Features : Attributes of the customer such as the credit history, loans, investments.
• Target : Represent whether a particular customer has defaulted in the past.

They are used for predicting discrete outcomes.

If the outcome can take two possible values then it is Binary Classification.

Whenever the outcome contains more than two possible values it is Multiclass Classification.

Machine learning algorithms for classification tasks

• Logistic Regression Classifier
• Decision Tree Classifier
• K Nearest Neighbor Classifier
• Neural Networks

REGRESSION

It is a supervised ML where algorithms learn from the data to predict continous values like salary, temperature, weight.

Machine learning algorithms for regression tasks.

• Linear Regression
• Decision Tree Regressor
• Random Forest Regressor
• Neural Networks
• K Nearest Neighbor Regressor

SUPERVISED V UNSUPERVISED

The key difference is that supervised uses labelled data.

Supervised learning models produce more accurate results than unsupervised however they rewuire human interaction at the outset in order to correctly identify the data.

Unsupervised learning models work in an autonomous manner to help identify the innate structure of data that has not been labelled.

USE CASES

For supervised the use cases are two: classification and regression.

In both tasks a supervised algorithm learns from the training data to predict something.

For unsupervised clustering and anomaly detection are the two key use cases.

GOALS

1. In supervised the aim is to forecast results for new data based in a model that has learned from labelled training dataset.
2. Under unsupervised the aim is to derive insights from massive amounts of data without explicit labels.

COMPLEXITY

Supervised LM is straightfoward relative to unsupervised.

Unsupervised LM require a large training set so as to yield the desired results hence they are computationally complex.