MACHINE LEARNING

The name itself specifies that it is the capability of a machine to learn itself. It does not require any explicit programming, instead it uses the previous data to predict the future. It is mainly focused on how to use the data and algorithms to imitate how humans learn and improve accuracy through experience. Machine learning is a growing technology in the field of data science which enables the computer to learn automatically from the past data and build predictions using historical information. The term machine learning was first introduced by Arthur Samuel in 1959.

Machine learning is the combination of computer science and statistics. The more we provide the data , the higher will be the efficiency of a machine. It is a data driven technology. It is similar to data mining as it deals with huge amount of data. Machine learning algorithms are created using frameworks. Machine learning is very useful for us as it has ability to do multiple and complex tasks where human feels it hard to do. It replaces the complexity of a problem . This can reduce both time and money.

CLASSIFICATION

• Supervised learning


• Unsupervised learning


• Reinforcement learning


• Semisupervised learning

SUPERVISED LEARNING

It is also known as Supervised machine learning. It uses labelled datasets to predict the outcomes accurately. Methods in supervised learning are neural networks, logistic regression and linear regression.

UNSPERVISED LEARNING

It is also known as Unsupervised machine learning. It is used to analyze unlabelled datasets to discover hidden patterns . The methods are principal component analysis (PCA) and singular value decomposition (SVD).

REINFORCEMENT LEARNING

This model approaches trial and error method. It is similar to supervised learning but , the algorithm does not use sample data. It's performance improves through feedbacks.

SEMISUPERVISED LEARNING

It acts as a bridge between supervised learning and unsupervised learning. It analyses small group of labelled data for classification and uses feature extraction from large group of unlabelled datasets.

IMPORTANCE OF MACHINE LEARNING

• Rapid increment in the production of data.
• Solving complex problems, which are difficult for a human.
• Decision making in various sector including finance.
• Finding hidden patterns and extracting useful information from data.

APPLICATIONS

Machine learning has got a great advancement in its research and it is widely used in huge areas such as Amazon Alexa, Catboats, recommender system,weather prediction, disease prediction, stock market analysis, etc. Some of the notable and major fields in which machine learning is used are

1. Rainfall prediction using Linear regression
2. Speech recognition
3. Business intelligence
4. Identifying handwritten digits using Logistic Regression in PyTorch
5. Fraud detection
6. Human resource relationship management
7. Kaggle Breast Cancer Wisconsin Diagnosis using Logistic Regression
8. Computer vision
9. Self driving cars
10. Face recognition