What is Machine learning?
This is the science of getting computer to act without programming. Deep learning is a subset of machine learning, is a Very simple term can be thought of as the automation of predictive analytics.
There are three types of Machine learning algorithm:
1.Supervised learning :Datasets should be digitized and new detected with them and new datasets cannot be leveled, as cannot be specified.
Learn to predict target values from labeled data.
• Classification
• Regression
Classification:
The classification algorithm is used when our output variable categories such as True-False, Yes-No, Male-Female etc.
Classification algorithm :
• Random Forest
• Decision Trees
• Logistics regression
• Support vector machine
Regression:
This algorithm is used when there is a relationship between input and output variables or independent or dependent functions. It helps in predicting continuous variables like weather forecasting, market tends etc.
Regression algorithm :
• Linear Regression
• Regression Trees
• Non-linear Regression
• Bayesian Linear Regression
• Polynomial Regression
2.UnSupervised learning :Datasets are not leveled and data sets are sorted based on their similarities or differences.
Finding useful resources or knowledge from data when no labels are available
1. Finding clusters or similar users.
2. Detecting abnormal server access pattern.
Unsupervised Learning is type of machine learning in which models are trained using unlabeled dataset and are allowed to act on that data without any supervise.
The goal of unsupervised learning is:
• To find the underlying structure of dataset
• Group that data accordingly similarities
• Represent dataset in a compress form.
Unsupervised learning is 2 types :
1. Clustering
2. Association
Clustering:
Clustering is a process in which the objects that are the same are in one group and the ones that are not in the same category are in another group.
Association:
This algorithm is used when it comes to extracting independency between variables from many large datasets. It pulls out a set of some items that stay together in a dataset. Very effective in Association Marketing Strategy. For example, if a person buys a product X (bread), then we can also say that the person has the potential to buy Y (butter, jam).
Unsupervised learning algorithm :
• K-means clustering
• KNN(K-Nearest neighbor)
• Hierarchical clustering
• Anomaly Detection
• Neural Network
• Principal Components Analysis
• Singular Value Decomposition
