Order the reasoning steps for when bigger models and more data are likely to help.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Which two approaches are usually the most dependable ways to improve a supervised learning system's performance?
True or False: When a model is underfitting, the only dependable way to improve it is to collect more labeled examples.
A photo-tagging system is missing subtle patterns. What word completes this advice: increase the capacity of the _____ and train on more labeled examples?
Which pair is a dependable way to improve an ML system today?
True or False: In many modern machine learning settings, increasing model size and adding more training examples are dependable ways to improve performance.
A practical way to improve a machine learning system is to build a larger _____ and add more data.
Match each model-improvement strategy to its description.
Order the steps for using the two dependable ways to improve a model.
Why are larger models and more data often called dependable ways to improve performance?
True or False: Collecting more labeled data is usually an unreliable way to improve a model.
A practical way to improve a model is to use a larger network and more _____.
Match each training limitation to the most direct improvement lever.
Two Dependable Ways to Improve Model Performance
Choosing the Most Dependable Ways to Improve a Model
Two Practical Ways to Improve an Algorithm