What is Machine Learning? Google Professional Data Engineer GCP

• an application of artificial intelligence
• where a computer/machine learns from the past experiences (input data)
• and makes future predictions.
• The system performance should be at least human level.
• ML provides enables machines to learn autonomously based on experiences, observations and analysing patterns within a given data set without explicitly programming.
• Process – we input a data set, machine will learn by identifying and analysing patterns and learn to take decisions autonomously
• Example – Facebook’s facial recognition algorithm

Components

All ML algorithm have three components:

• Representation: how to represent knowledge like decision trees, sets of rules, etc.
• Evaluation: how to evaluate candidate programs (hypotheses) like accuracy, prediction and recall, likelihood, etc
• Optimization: how candidate programs are generated or the search process like combinatorial optimization, convex optimization, constrained optimization.

Types of Learning

There are four types of machine learning:

• Supervised learning: (or inductive learning) Training data includes desired outputs like identify spam, learning is supervised. It is most mature and  Defined as – if data is (x) and the output is (f(x)), goal is to learn the function for new data (x). Techniques include
  • Classification: when the function being learned is discrete.
  • Regression: when the function being learned is continuous.
  • Probability Estimation: when the output of the function is a probability.
• Unsupervised learning: Training data does not include desired outputs like clustering.
• Semi-supervised learning: Training data includes a few desired outputs.
• Reinforcement learning: Rewards from a sequence of actions.