LINKED LIST [txt mode] ▸ @stats385 ▸ Landmark architectures
home explore | log in

Landmark architectures

by @stats385 · last added 2026-09-24 · 10 items [architectures]

AlexNet through ResNet plus Dropout, BatchNorm, visualization, and the rethinking-generalization paper.

* LeNet-5 (LeCun et al.)
Pioneering digit CNN — historical root of modern convnets; banks used it for checks.
yann.lecun.com · node›
* Generative Adversarial Networks (Goodfellow et al.)
GANs as a landmark generative architecture — course ‘extra’ but culturally essential.
arxiv.org · node›
* Understanding Deep Learning Requires Rethinking Generalization
Zhang et al. — nets can memorize random labels; forced a rethink of classical generalization.
arxiv.org · node›
* Zeiler & Fergus — Visualizing CNNs
Classic visualization paper — how to see what conv layers learn.
cs.nyu.edu · node›
* Batch Normalization
Stabilized deep training by reducing internal covariate shift; changed how nets are built.
arxiv.org · node›
* Dropout (Srivastava et al.)
Simple regularization that prevents co-adaptation — still a default trick students should know.
jmlr.org · node›
* ResNet — Deep Residual Learning
Residual blocks unlocked 100+ layer nets; still the mental model for modern architectures.
arxiv.org · node›
* GoogLeNet / Inception
Going Deeper with Convolutions — multi-scale inception modules and careful compute budgeting.
arxiv.org · node›
* VGG — Very Deep Convolutional Networks
Showed depth with small 3×3 filters; became the default feature backbone for years.
arxiv.org · node›
* AlexNet (Krizhevsky, Sutskever, Hinton)
2012 ImageNet breakthrough — launched the modern deep CNN era. Know the architecture sketch.
papers.nips.cc · node›
privacy | terms | regular mode