Tuning Auxiliary Data Weight with the Dev Set
A weighted objective can use an additional parameter, beta, for the auxiliary internet-image data. Setting beta to 1/40 gives equal total weight to 5,000 mobile images and 200,000 internet images, and other beta values can be selected by tuning on the dev set.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Related
Tuning Auxiliary Data Weight with the Dev Set
Which condition makes it appropriate to down-weight auxiliary training data according to Andrew Ng?
Down-weighting auxiliary data can reduce the computational burden of training a model on both auxiliary and target-distribution examples.
Re-weighting is needed only when you suspect the additional data has a very _____ distribution than the dev/test set.
Match each training scenario to its key implication for handling auxiliary data.
Order the reasoning steps a practitioner should follow when deciding whether to down-weight large-scale auxiliary training data.
In the 40x internet vs. mobile image scenario, what is the main cost of training equally on both sources without down-weighting?
Giving auxiliary data a lower weight in training is equivalent to removing it from the training set entirely.
By giving internet images a much lower _____, you don't have to build as massive a neural network.
Match each concept to its correct description in the context of auxiliary data down-weighting.
Order the causal steps explaining why down-weighting auxiliary data allows a smaller neural network to be used.