Deep Learning / 29
Efficient Deep Learning
Examine computation, memory, compression, precision, and distributed training choices.
This is a knowledge index. Published titles open their articles; the remaining entries outline planned coverage.
Subtopics
- 29.01
Why Efficiency Matters
Planned guide: Why Efficiency Matters. Focus on intuition, assumptions, and a worked example.
- 29.02
Parameter Count
Planned guide: Parameter Count. Focus on intuition, assumptions, and a worked example.
- 29.03
FLOPs
Planned guide: FLOPs. Focus on intuition, assumptions, and a worked example.
- 29.04
Memory Usage
Planned guide: Memory Usage. Focus on intuition, assumptions, and a worked example.
- 29.05
Quantization
Planned guide: Quantization. Focus on intuition, assumptions, and a worked example.
- 29.06
Pruning
Planned guide: Pruning. Focus on intuition, assumptions, and a worked example.
- 29.07
Knowledge Distillation
Planned guide: Knowledge Distillation. Focus on intuition, assumptions, and a worked example.
- 29.08
Low-Rank Approximation
Planned guide: Low-Rank Approximation. Focus on intuition, assumptions, and a worked example.
- 29.09
Mixed Precision
Planned guide: Mixed Precision. Focus on intuition, assumptions, and a worked example.
- 29.10
Gradient Accumulation
Planned guide: Gradient Accumulation. Focus on intuition, assumptions, and a worked example.
- 29.11
Model Compression
Planned guide: Model Compression. Focus on intuition, assumptions, and a worked example.
- 29.12
Efficient Architectures
Planned guide: Efficient Architectures. Focus on intuition, assumptions, and a worked example.
- 29.13
Sparse Models
Planned guide: Sparse Models. Focus on intuition, assumptions, and a worked example.
- 29.14
Distributed Training
Planned guide: Distributed Training. Focus on intuition, assumptions, and a worked example.