Skip to main content
← Choose a different target

Unlock: Weight Initialization

Why initialization determines whether gradients vanish or explode, and how Xavier and He initialization preserve variance across layers.

127 Prerequisites0 Mastered0 Working111 Gaps
Prerequisite mastery13%
Recommended probe

McDiarmid's Inequality is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.

Weight InitializationTARGET
McDiarmid's InequalityAdvancedWEAKEST
Not assessed13 questions
Sub-Exponential Random VariablesCore
Not assessed2 questions
Sub-Gaussian Random VariablesCore
Not assessed15 questions
Symmetrization InequalityAdvanced
Not assessed3 questions
VC DimensionCore
Not assessed58 questions
Contraction InequalityAdvanced
Not assessed1 question
Activation FunctionsFoundations
Not assessed36 questions
Eigenvalues and EigenvectorsAxioms
Not assessed20 questions
Feedforward Networks and BackpropagationCore
Not assessed17 questions

Sign in to track your mastery and see personalized gap analysis.