Summary Data science

Types of Machine Learning Paradigms



Supervised Learning and Labeled Data

 Involves a target/outcome variable (or dependent variable) which is to be predicted from a
given set of predictors (independent variables)
 Training dataset contains examples of input-output pairs

Unsupervised Learning and Pattern Recognition

 Does not involve a target/outcome variable to be predicted
 Aims to model the underlying structure or distribution in the data
 Mainly used for clustering and association

Reinforcement Learning and Feedback Mechanisms

 An agent learns to behave in an environment, by performing certain actions and observing the
results/rewards
 The goal is to learn a series of actions that maximizes the final reward

Key Factors Enabling Machine Learning in Today's Era

 Large amounts of data
 Increased computational power
 Advancements in algorithms and techniques
 Greater accessibility and affordability of tools and platforms

Applications of Machine Learning in Real Life

 Image and speech recognition
 Natural language processing
 Predictive maintenance
 Recommendation systems
 Fraud detection
 Self-driving cars
 Personalized medicine

Basic Terminologies

 Training set: A dataset used to train a machine learning model.
 Test set: A dataset used to evaluate the performance of a trained model.
 Overfitting: A model that performs well on the training data but poorly on new, unseen data.
 Underfitting: A model that fails to capture the underlying trends in the data.