We are living in the most defining period of human history. Here the computer moves from large mainframe PC to Containers and Cloud.
We will create a new world where Intelligent computers and smart devices who can take decisions and can improve their behavior from past experience, yes we are talking about Machine learning.
The language used: R & Python
There are 3 types of ML Algorithms :
- Supervised Learning
- Un-Supervised Learning
- Reinforcement Learning
1. Supervised Learning
This approach consists of Target/outcome data or variables (dependent) which is to be predicted from a given set of data (predictors), Using these set of variables we generate functions to map the input to there output
Here the training process continues till the desired stage of accuracy on the training data.
Example: Regression, Decision Tree, Random Forest, KNN, etc.
2. Un-Supervised Learning:
Here we don’t have target or outcome variables to be predicted or estimated, It is used for clustering population in different groups
Example: Apriori algorithm, K-means
3. Reinforcement learning :
Here we train a machine to make a specific decision, where machine exposed to an environment where it trains continuously using trail and error.
Here will learn from past experience and tries to capture the best possible knowledge to make an accurate decision
Example: Markov Decision process
List of command and popular machine learning algorithms :
- Decision Tree
- Linear Regression
- Logistic Regression
- Naive Bayes
- Random Forest
- Dimensionality Reduction Algorithm
- Gradient Boosting Algorithm