Gids-gekoppelde quiz · Middelmatig Niveau
Groepsnormalisatiequiz
Test per voorbeeld kanaalgroepen, gedrag in kleine batches, beperkende gevallen, aangeleerde affiene parameters en bewijsmateriaal uit evaluatie-instellingen.
Vraag 1 van 8
Over welke dimensies berekent Groepsnormalisatie statistieken?
Bekijk elke vraag8 vragen
Antwoorden en uitleg verschijnen terwijl je de quiz doet.
- Over welke dimensies berekent Groepsnormalisatie statistieken?
- Only across examples in the batch
- Across all model layers
- Across the training and validation sets together
- Spatial dimensions and channels within a group for each sample
- Waarom kan GroupNorm voor zeer kleine batches de voorkeur verdienen boven BatchNorm?
- It uses the batch mean more accurately with one sample
- Its statistics are independent of batch size
- It removes all learned scale parameters
- It requires a larger batch
- How does GroupNorm divide feature channels?
- Into groups, then normalizes each group’s values within each example
- Into classes across the dataset
- Into separate networks for each batch member
- Into groups based on labels only
- Wat betekent de onafhankelijkheid van GroupNorm van batchgrootte?
- Its output is identical for all batch sizes and all models
- It eliminates the need for training batches
- Its per-example normalization does not use other examples’ statistics
- It guarantees the same accuracy on every task
- Welke GroupNorm-instelling komt overeen met één groep die alle kanalen bevat?
- Batch-normalisatie
- Normalisatie van lagen
- Instance Normalization
- Weight Normalization
- Welke GroupNorm-instelling komt overeen met één kanaal per groep?
- Normalisatie van lagen
- Batch-normalisatie
- RMS Normalization
- Instance Normalization
- What does each channel’s learned scale and shift do after normalization?
- Sets the group membership from labels
- Computes batch statistics
- Allows the network to adjust the normalized feature values
- Removes the normalized activations
- What is a careful interpretation of GroupNorm’s reported results?
- It performed well in tested small-batch vision settings; task-specific evaluation remains needed
- It replaces every normalization method in all networks
- It guarantees identical results for every batch size and task
- It removes the need to tune group count