Neural Networks & Deep Learning¶
What this subject is for: The architectural primitives every modern model is built from — MLPs, CNNs, RNNs, residuals, normalization, optimization, scaling laws.
Track status: 9 substantive concept pages · 3 stubs awaiting next cycle. See the live generation status and the latest retrospective.
Concepts¶
- Backpropagation
- Batch normalization
- Gradient Descent
- Normalization
- Optimization
- Regularization in Large Model Fine-Tuning
- Residual connections
- Scaling laws in neural networks
- Transformer Architecture
Auto-seeded stubs awaiting next cycle: adaptive-optimizers, layer-normalization, residual-networks
Arcs through this subject¶
No arcs yet — the retrospective proposes these once concept coverage hits ≥4 pages per track.
Key thinkers¶
Author pages pending.
Builds tied to this subject¶
MVB recipes pending — currently they live inside concept pages' Build it sections.
Auto-rebuilt from filesystem state by scripts/rebuild_track_indexes.py — see system architecture.