Unlock: Transformer Architecture
The mathematical formulation of the transformer block: self-attention, multi-head attention, layer normalization, FFN blocks, positional encoding, and parameter counting.
169 Prerequisites0 Mastered0 Working143 Gaps
Prerequisite mastery15%
Recommended probe
Chernoff Bounds is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.
Transformer ArchitectureTARGET
Not assessed3 questions
McDiarmid's InequalityAdvanced
Not assessed13 questions
Not assessed2 questions
Not assessed15 questions
Symmetrization InequalityAdvanced
Not assessed3 questions
VC DimensionCore
Not assessed58 questions
Contraction InequalityAdvanced
Not assessed1 question
Adam OptimizerCore
Not assessed11 questions
Deep Learning (Goodfellow, Bengio, Courville)Infrastructure
No quiz
Not assessed17 questions
Not assessed5 questions
Softmax and Numerical StabilityFoundations
Not assessed11 questions
Attention Mechanism TheoryResearch
Not assessed11 questions
Attention Mechanisms HistoryAdvanced
Not assessed3 questions
Convolutional Neural NetworksAdvanced
Not assessed1 question
No quiz
Recurrent Neural NetworksAdvanced
Not assessed3 questions
Not assessed2 questions
Word EmbeddingsCore
Not assessed6 questions
Byte-Level Language ModelsResearch
No quiz
No quiz
RNNs for Signal SequencesResearch
No quiz
Sign in to track your mastery and see personalized gap analysis.