Learn Before
Why Increasing Model Size and Data Eventually Stops Helping
In theory, making a neural network larger and giving it more training examples can improve performance on many tasks. In real projects, however, very large models take much longer to train, and the pool of additional data can run out.
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
Why enlarging a model can lower bias
Using More Data When Variance Is High
Why Increasing Model Size and Data Eventually Stops Helping
Methods to Reduce High Avoidable Bias
Ways to Reduce High Variance
What should you do when avoidable bias is high?
True or false: When a model has high variance, adding more training examples is often a useful remedy.
For persistent underfitting, increase the _____ of the model.
Match each learning problem or model change with the usual remedy or meaning.
Order the steps for applying a simple model-fix rule.
How the diagnosis determines the fix for bias and variance
Select the right remedy for bias and variance in two projects.
State the recommended fix for each training problem.
Which option applies the rule of thumb correctly to both cases?
Bias and variance call for the same fix
Learn After
What is the main practical limit on repeatedly making a neural network much larger?
True or False: With enough model capacity and enough labeled data, a learning system can in principle achieve strong results on many tasks.
Training a very large model is _____, so increasing model size has practical limits.
Match each scaling approach with the limitation it eventually runs into.
Order the steps that explain why model and data scaling have practical limits.
Why Infinite Scaling Is an Idea, Not a Plan
Practical limits when scaling a fraud model
What two practical bottlenecks limit endless growth in model size and training data?
What can stop a team from relying on ever more training data?
True or False: Making a neural network much larger always makes training faster and removes compute bottlenecks.