Remember-formulate-predict framework

As explained in Grokking Machine Learning

The remember-formulate-predict framework is a machine-learning workflow that examines previous data, builds a model from it, and applies the model to future data.

The remember-formulate-predict framework describes how decisions can be made from experience: examine previous data, formulate a general rule, and use that rule to predict what may happen next. In machine learning, the rule is a model built from data. section 1.3

The workflow has three steps:

• Remember: look at previous data. section 1.4
• Formulate: build a model or rule from that data. section 1.4
• Predict: use the model to make predictions about future data. section 1.4

Guessing whether it will rain

Remember that it rained most of last week; formulate the rule that it rains most of the time in this place; predict that it will rain today. The guess may be right or wrong, but it uses the available experience. section 1.3

Figure 1.4 The remember-formulate-predict framework is the main framework we use in this book. It consists of three steps: (1) We remember previous data; (2) we formulate a general rule; and (3) we use that rule to make predictions about the future.

A diagram of the three steps: remember previous data, formulate a general rule, and use it to predict the future. section 1.3

How Grokking Machine Learning covers it

How deep it goes

Defines three workflow steps and connects the formulated rule to a model used for prediction.

Examples

Uses remembered rainy weather to formulate a rule and predict whether it will rain today.

What you can do after

Apply the workflow by reviewing past data, formulating a rule, and using it to predict future data.

How it connects

Connects machine learning with models: rules representing data that can be used to make predictions.

liveBookmanning.com

Read Grokking Machine Learning on liveBook Get the book at manning.com

Related concepts

• machine learningused by · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
• language modelproduces · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.

This explainer was generated by Manning's knowledge graph from the text of Grokking Machine Learning. The section links point to the parts of the book it draws on.