Learn Before
What should happen after an experiment ends?
Question: In an iterative machine learning workflow, a team has implemented an idea and run an experiment. What should they do next with the outcome?
Sample answer: They should use what they learned to come up with new ideas and continue the iteration cycle.
Key points:
- Use the experiment result to generate new ideas.
- Keep iterating.
Rubric: The student must state that the team should use the experimental results to produce new ideas and continue iterating.
0
1
Tags
D2L
Dive into Deep Learning @ D2L
Machine Learning
Deep Learning
Supervised Learning
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Faster Experiment Cycles Improve Learning Speed
Evaluate Several Model Improvements at the Same Time
Share Machine Learning Lessons With the Team
What three-step cycle best describes a fast machine-learning development loop?
Does the first design you test in an ML project usually become the final solution?
Model Improvement Usually Takes Many Iterations
Match each stage in a simple development cycle with its role.
Put the machine learning improvement cycle in the right order.
Why Machine Learning Development Repeats in Cycles
What should a team do after the first experiment makes things worse?
What should happen after an experiment ends?
What is the main purpose of running a trial in an iterative machine learning workflow?
Must you often test many ideas before finding a workable machine learning solution?