1. Introduction to AI

All models a re wrong but some are useful

• AI models and how to build it

Model

• simplified representation of a process or a system
• complexity and accuracy requirements defined by the application.

How do we build one?

1. Define the problem
2. collect the data
3. configure & fit the model
4. use it!

Define the problem

• poor problem definition = highway to disaster
  • no success measure, no value proposition
  • EX. automatic the task

Key questions

1. how do we create value by solving thi
2. how we create. a value to solve problem
3. How do we know

All models are wrong but some are useful | Python

Congifure the model