Mistakes to Avoid in Machine Learning

Building machine learning models can be an exciting process. But oftentimes, data scientists find themselves dealing with errors, bad output, and a host of other issues that can slow their progress. In this fast-paced course, get expert tips on how to avoid some of the most common mistakes data scientists make when building machine learning models. Instructor Brett Vanderblock, the lead data scientist at Patagonia, shares his expertise to help you fine-tune your machine learning workflow. From working with bad data, to overfitting, to not getting feedback, there's lots to learn.

This course was created by Madecraft. We are pleased to host this training in our library.

课程信息

  • 英文名称:Mistakes to Avoid in Machine Learning
  • 时长:39分50秒
  • 字幕:英语

课程目录

  1. Avoiding machine learning mistakes
  2. Using the exercise files
  3. Assuming data is good to go
  4. Neglecting to consult subject matter experts
  5. Overfitting your models
  6. Not standardizing your data
  7. Focusing on the wrong factors
  8. Data leakage
  9. Forgetting traditional statistics tools
  10. Assuming deployment is a breeze
  11. Assuming machine learning is the answer
  12. Developing in a silo
  13. Not treating for imbalanced sampling
  14. Interpreting your coefficients without properly treating for multicollinearity
  15. Evaluating by accuracy alone
  16. Giving overly technical presentations
  17. Take your machine learning skills to the next level

评论