Start by establishing a clean, reproducible baseline with a simple model and stratified splits, then systematically diagnose data issues (noise, corruption, imbalance) using model-derived signals and data-centric methods. Propose a pipeline that detects and filters bad samples, applies imbalance mitigation, and compares advanced training strategies (confidence pruning, co-teaching, MixUp/CutMix) via controlled experiments with proper metrics.
Pro tip: Emphasize that you always validate data quality improvements on a small, manually verified clean holdout set to avoid overfitting to noisy validation metrics, and that you track both overall accuracy and per-class recall to catch hidden biases.
Train a simple model (e.g., ResNet-18) on a stratified split that preserves class distribution and isolates a clean validation set. Use cross-validation or a fixed holdout to ensure reliable evaluation.
Analyze label noise via confusion matrices, loss distributions, and confident learning; detect corrupted samples via outlier detection or reconstruction error; quantify class imbalance with class frequencies and per-class performance.
Filter noisy/corrupted samples using confidence-based pruning or cleanlab, and address imbalance with class weighting, resampling, or focal loss. Re-evaluate on the clean holdout.
Experiment with co-teaching (two networks select clean samples for each other), MixUp/CutMix augmentations, and combinations. Use A/B testing with statistical significance to compare against baseline and simpler methods.
Continuously monitor model performance on the clean holdout, adjust thresholds and strategies, and document trade-offs (e.g., computational cost vs. accuracy gain).
AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.
Start by clearly defining the network architecture and forward pass equations, then derive the gradients analytically for each layer. Implement the backward pass using these gradients, validate with numerical gradient checking, and discuss practical considerations like numerical stability, initialization, regularization, and CNN extensions.
Pro tip: Emphasize the importance of vectorized implementations and numerical stability tricks (e.g., log-sum-exp) to demonstrate production-level awareness. Also, mention that gradient checking should be done in double precision and with a small subset of parameters to avoid computational overhead.
Specify the two-layer network: input -> linear -> ReLU -> linear -> softmax. Write the forward pass equations in NumPy, including the softmax cross-entropy loss with numerical stability (subtract max logits).
Compute gradients of the loss w.r.t. parameters and inputs using backpropagation. For softmax cross-entropy, the gradient w.r.t. logits is (probs - one_hot). Then propagate through the second linear layer, ReLU, and first linear layer.
Code the backward pass using the derived gradients, ensuring vectorized operations. Cache intermediate values (e.g., activations, pre-activations) during forward pass for use in backward pass.
Implement a numerical gradient checker using finite differences. Compare analytical gradients with numerical ones for a small random subset of parameters, ensuring relative error is below a threshold (e.g., 1e-7).
Cover numerical stability (log-sum-exp, avoiding overflow), weight initialization (He initialization for ReLU), regularization (L2, dropout), and how to extend to CNNs (convolutional layers, pooling, and their backward passes).
AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.