Machine Learning

Machine learning is a branch of artificial intelligence (AI) and computer science which used data and algorithms for the training of computer program to learn from data and make prediction on the basis of learned data. Machine Learning is the study of making machines more human-like in their behavior and decisions by giving them the ability to learn and develop their own programs. This is done with minimum human intervention. The learning process is automated and improved based on the experiences of the machines throughout the process.

There is a difference between traditional programming and machine learning. In traditional programing we feed input in the form of set of instruction to machine to generate output. While in machine learning we feed input and output for the learning of training model. Based on our trained model, we get prediction from machine to newly come/un-seen data.

To illustrate the difference between traditional programming and machine learning, below given figure will help to better understand.

Traditional Programming vs Machine learning

Machine learning methods

Machine learning classified into three categories.

1. Supervised Learning
2. Unsupervised Learning
3. Semi-Supervised Learning
4. Supervised Learning

Supervised learning in which data is labelled( labelled means input data is already tagged with the correct output)used for training. And after the completion of training of each data, the model is tested on the basis of test data (a subset of the training set), and then it predicts the output.

Supervised learning is divide into:

a) Classification: Various labels train the algorithm to identify items within a specific category. E.g., Disease or no disease, Beer or wine.

b) Regression: Used to predict future values and the model is trained with the historical data. E.g., Predicting the future price of a product.

2. Unsupervised Learning

Unsupervised learning uses machine learning algorithms to analyze and cluster unlabeled datasets. In unsupervised learning models itself find the hidden patterns and insights from the given data.

Unsupervised learning is divide into:

a) Association: Association rule is used to find relationship between variable in large data set. E.g., Association rules are used for marketing like if customer A purchase Bread he will also purchase Milk.

b) Clustering: Clustering in other term used for grouping. Objects that have same most similarities will cater into one cluster and group having same but less or not will cater into another group.

3. Semi-Supervised Learning

Semi-supervised is a medium between supervised and unsupervised learning. It uses the combination of labeled and unlabeled datasets during the training period. Semi-supervised learning can solve the problem of having not enough labeled data to train a supervised learning algorithm.

Steps of Machine Learning

1. Data Collection
2. Data Preparation
3. Selecting a model
4. Training
5. Testing
6. Evaluation
7. Hyperparameter Tuning
8. Prediction