← UDL vault · mid-sem exam guide

UDL mid-sem exam guide -- previous papers + slides.

udlexam-guideprevious-yearmid-sem

Extra mid-sem guide built from previous-year EC-2 regular/makeup papers, Lecture 8 tips and slide emphasis. Use it after one pass through cheatsheet and before solving papers.

Priority order

RankTopicWhy high priorityPractice page
1Autoencoder/CNN calculationsRepeated in previous papers and Lecture 8: activation/loss, BCE, backprop, Conv2D shapes, params, pooling effects.Solved autoencoders
2Normalizing flowsFlow transform, invertibility, RealNVP masks/log determinant, dequantization recur across paper and slides.Solved flows
3MADE / autoregressive modelsSampling order and mask diagrams are likely conceptual+diagram marks.Solved AR
4PCA/ICA/complexityShort marks: complexity, ICA application, incremental PCA disadvantages.Cheatsheet PCA
5PixelCNN familyComparison marks: Gated PixelCNN, PixelCNN++, PixelSNAIL.Slides explained

Previous-year pattern

  • Q1 style: Autoencoder/CNN calculation. Usually activation/loss/backprop or transposed convolution.
  • Q2 style: Probability/MLE or RealNVP transform.
  • Q3 style: PCA complexity, ICA application, PixelCNN/flow conceptual subparts.
  • Q4 style: MADE masks/sampling plus PixelCNN/WaveNet/PixelSNAIL comparison.

How to write answers

Question typeWrite this firstCommon loss
Conv/AE numericalLayer shape formula, parameter formula, then substituted numbers.Skipping bias term or pooling shape.
AE activation/lossData type: binary/one-hot/real-valued. Then activation and loss.Using MSE for binary without justification.
PCA/ICAObjective difference: variance vs independence.Saying ICA = PCA with different name.
MADE maskWrite factorization and dependency rule before drawing edges.Allowing output \(x_i\) to see \(x_i\) or future variables.
FlowWrite invertible map, inverse if needed, Jacobian/log-det.Forgetting absolute determinant or dequantization reason.

One-day crash plan

  1. 60 min: cheatsheet + formula sheet.
  2. 90 min: solve autoencoder/CNN and flow solved-paper questions without expanding answers.
  3. 45 min: MADE masks, PixelCNN family comparison, Parallel WaveNet.
  4. 45 min: PCA complexity, ICA/CCA/LLE quick comparisons.
  5. 60 min: run question bank orally, then check weak spots.

Must memorize

  • Conv2D params and output shape.
  • Transposed convolution output shape.
  • BCE and MSE choices.
  • Laplace MLE: median + mean absolute deviation.
  • Autoregressive factorization.
  • Flow change-of-variables formula.
  • RealNVP affine coupling and log-det.
  • PixelCNN -> Gated PixelCNN -> PixelCNN++ -> PixelSNAIL improvement chain.
  • Continuous point probability equals zero.
Exam-room rule. For every numerical, write formula before substitution. For every comparison, write one line for mechanism and one line for tradeoff.
← solved papercheatsheet →
© cvam -- written in plaintext, served warm