Day 5 - Week 7 Synthesis: Deep Learning Summary

Week 7 progressed from neural network basics (Day 1) → CNN (Day 2) → RNN/sequences and Transformer (Day 3) → learning techniques and transfer learning (Day 4). Today we consolidate this progression into a single decision map and establish a thought framework for quickly narrowing down answers when encountering deep learning questions in the exam.

Deep Learning Map at a Glance

Select architecture by data type
  ├─ Structured/tabular data    → Usually XGBoost first, DNN secondary
  ├─ Images/video               → CNN (ResNet/SSD/U-Net)
  ├─ Sequences (time series, text) → RNN/LSTM/GRU, or Transformer
  └─ Large-scale language/generation → Transformer (BERT/GPT/T5)