Training Dev Set
A training dev set is a separate subset split from the available training data that the algorithm does not train on. It is drawn from the same distribution as the training set and only needs to be large enough to evaluate and track learning progress.
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
Avoid Randomly Shuffling Mixed-Source Data into Dev/Test Sets
Include Some Target-Distribution Examples in Training Alongside Auxiliary Data
Down-Weighting Auxiliary Data from a Different Distribution
Training Dev Set
Error Table Across Two Data Distributions and Three Error Types
Data Mismatch Between Training and Dev Set Distributions
Limited Practical Scope of Domain Adaptation for Different Data Distributions
Domain Adaptation for Different Data Distributions
Website Images and Mobile Phone Pictures as a Distribution Mismatch Example
Random 70/30 Train/Test Split Can Fail Under Distribution Shift
Which data should define the dev and test sets for the cat-picture app?
Dev and test sets should represent the future data distribution of interest.
Complete the principle: Dev and test sets should reflect _____ data.
Match each cat-app data group with its appropriate role or property.
Order the decisions for building datasets when auxiliary and target data differ.
Explain why different training and evaluation distributions can be appropriate.
Diagnose the evaluation-set mistake in a mobile cat-classification app.
Why did success on website images fail to ensure success on mobile uploads?
Which dataset design best uses both target and auxiliary cat images?
Using extra internet images for training requires internet images in dev and test sets.
Learn After
Four Dataset Evaluation for Different Training and Dev/Test Distributions
Training Dev Set Size Guidelines
What distinguishes a training dev set from the actual training set?
Is the training dev set drawn from the training set's distribution?
The algorithm does not _____ on the training dev set.
Match each dataset feature to its role in a training-dev split.
Order the steps for creating and using a training dev set.
Explain why a training dev set is held out despite sharing the training distribution.
Diagnose the flaw in a team's proposed training-dev split.
How large does a training dev set need to be?
Which proposed split correctly creates a training dev set?
Must a training dev set be the same size as the actual training set?