// ⬡ Deep Learning Foundations
Adam
A momentum optimizer with per-parameter adaptive step sizes.
Adam 优化器 2014 Foundational core
IN PLAIN WORDS
Tracks running means of gradients (momentum) and squared gradients, scaling each parameter's step. It is the default deep learning optimizer.
Used in: Nearly all neural-network training
01Original paper
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · 2014
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Related:Muon Optimizer
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Explainers
Official docs
Books
04Where the course teaches it
U14 PyTorch & Autograd Tensors, autograd, data loading and the training loop. 10 h2 algorithms0 papers U31 Training Deep Nets SGD/momentum/Adam/AdamW/Muon, learning-rate schedules, BatchNorm/LayerNorm/RMSNorm, dropout and residuals. 10 h10 algorithms4 papers
On learning paths:Zero to Deep Learning
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
adam)