Neural Architecture Search Quiz

Answers and explanations appear as you take the quiz.

1. What does Neural Architecture Search automate?
   • The design of the neural network's structure
   • Labeling training data
   • Cooling the GPU servers
   • Writing documentation for models
2. Which three components define a NAS method?
   • Dataset, optimizer, and dropout
   • Search space, search strategy, and performance estimation
   • Encoder, decoder, and attention
   • Training, validation, and test sets
3. What accelerator scale did the original reinforcement-learning NAS paper report for its large search?
   • One GPU for every NAS method
   • A fixed cost of exactly 1,000 GPU-days for every search
   • An experiment using 800 GPUs in that study
   • No accelerator use during architecture search
4. What key trick does DARTS use to make search efficient?
   • It trains on a single example
   • It removes all hidden layers
   • It uses only random search
   • It relaxes discrete architecture choices into continuous ones optimizable by gradients
5. What is a 'supernet' in weight-sharing NAS?
   • One over-parameterized network containing all candidate architectures, whose weights are shared
   • A network with billions of parameters
   • A network running on supercomputers only
   • A backup copy of the model
6. What did the HURRICANE hardware-aware NAS study evaluate?
   • One architecture that is guaranteed optimal on every device
   • Tailored architectures for three hardware types under matched latency constraints
   • A language model trained without any hardware measurements
   • A method that removes latency from architecture evaluation
7. What is one limitation of weight-sharing NAS supernets?
   • They remove all architecture choices
   • They guarantee the globally best architecture
   • The shared weights can bias architecture rankings relative to training each candidate independently
   • They do not use neural networks
8. What does a NAS evaluation need to report for a fair comparison?
   • Only the best test score
   • The GPU brand alone
   • The model name without settings
   • Search space, compute budget, validation protocol, and final retraining setup