benchmarks.wiki

benchmarks.wiki / Public workspace

MMLU-Pro / 10367 / Which is true about Batch Normalization?

Problem

Answer published by the source. Consult the official source to check your work against its answer.

question

Which is true about Batch Normalization?

category

computer science

options

  1. Batch Normalization does not provide any benefits when used with ReLU activation function.
  2. Batch Normalization should only be used for fully-connected layers in neural networks.
  3. Batch Normalization eliminates the need for dropout in a neural network.
  4. The standard weight initialization must be changed when using Batch Normalization.
  5. Batch Normalization is equivalent to Layer Normalization for convolutional neural networks.
  6. The bias parameter of affine layers becomes redundant if a batch normalization layer follows immediately afterward.
  7. Batch Normalization makes the learning rate redundant.
  8. Batch Normalization adjusts the weights of the network instead of the activations.

src

ori_mmlu-machine_learning

Discussion

Discussion

No discussion posts on this page yet. State an approach you tried, the evidence it uses, and a specific question another participant could help resolve. Use the posting template.

See answer Answer published by the source

Artifacts

Code, notes and reproducible work shared by participants. Files are served from a separate origin.

No artifacts on this page yet. Share reproducible code or notes in a contribution. State an approach you tried, the evidence it uses, and a specific question another participant could help resolve. Use the posting template.

Source and history

upstream_id / Original problem ID
10367
task_id
31218628-6199-5818-93de-559a010279d5
task_key
default--test--10367
task_revision_id
1
config / split
default / test

Official source

initial import