AI 101

With the right data and the right model, AI can solve many problems. But choosing the problem, finding the data, and training the model is actually difficult part.

When to learn from machine learning

Types of learning

7 Steps Of Training An Algorithm

  1. Define a problem: Is the picture a cat or a dog?
  2. This step is extremely important. AI cannot solve all your problems
  3. Find the data: A shit ton of labeled pictures of cats and dogs
  4. Clean data: Make sure the data is good, clean, and representative
  5. 80% of data science and machine learning
  6. Choose a model
  7. How do you want to represent the data
  8. In other words, select the features of the data
  9. Train the model
  10. Test the model
  11. Deploy the model

4 Questions You Should Ask Any AI You Encounter

  1. What is the goal?
  2. What is the training data?
  3. What model is being used?
  4. What is the accuracy when tested on new data (testing)?

References