Unlock: Batch Normalization

Normalize activations within mini-batches to stabilize and accelerate training, then scale and shift with learnable parameters.

147 Prerequisites0 Mastered0 Working132 Gaps

Prerequisite mastery10%

Recommended probe

Fisher Information: Curvature, KL Geometry, and the Natural Gradient is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.

Batch NormalizationTARGET

Fisher Information: Curvature, KL Geometry, and the Natural GradientInfrastructureWEAKEST

Not assessed19 questions

McDiarmid's InequalityAdvanced

Not assessed13 questions

Symmetrization InequalityAdvanced

Not assessed3 questions

VC DimensionCore

Not assessed58 questions

Contraction InequalityAdvanced

Not assessed1 question

Sufficient Statistics and Exponential FamiliesInfrastructure

Not assessed6 questions

Activation FunctionsFoundations

Not assessed36 questions

Expectation, Variance, Covariance, and MomentsAxioms

Not assessed41 questions

Feedforward Networks and BackpropagationCore

Not assessed17 questions

Gradient Flow and Vanishing GradientsCore

Not assessed7 questions

Regularization in PracticeCore

Not assessed5 questions

Skip Connections and ResNetsCore

Not assessed1 question

Weight InitializationCore

Not assessed1 question

Whitening and DecorrelationCore

No quiz