apply deep learning or not

 

Deciding when Deep Learning is the Right Tool

Deep Learning is a powerful tool, but it's not the only one. In general, the way to choose whether or not to use Deep Learning depends on your task, what kind of data you have, and how complex the relationships in the data are.

Scenarios in which to use Deep Learning include but are not limited to:

• Tasks
  • Binary classification:
    • Deep Learning
    • Logistic Regression
    • Decision Trees
    • Support Vector Machines
  • Multi-class classification:
    • Deep Learning
    • Decision Trees
    • Support Vector Machines
  • Regression:
    • Deep Learning
    • Linear Regression
    • some Decision Trees
• Data:
  • Images:
    • Deep Learning
  • Text:
    • Deep Learning
    • Statistical Methods
  • Tabular Data:
    • Decision Trees
• Data Relationships:
  • Simple:
    • Linear Regression
    • Logistic Regression
    • Decision Trees
  • Complex:
    • Deep Learning
    • Decision Trees

Additional Resources

If you want to learn more about when each machine learning method is appropriate, we recommend this article from MIT's Sloan school