Assess students' ability to apply pruning, quantization, and knowledge distillation to compress and deploy deep neural networks on resource-constrained edge devices; tasks include selecting and justifying appropriate techniques, designing an end-to-end compression and deployment pipeline, analyzing trade-offs (accuracy, latency, memory, energy), specifying implementation steps (e.g., structured vs unstructured pruning, PTQ vs QAT, teacher–student setups), and defining evaluation metrics and hardware-aware deployment strategies for a given edge scenario.