The Neural Network Zoo: one chart mapping dozens of NN architectures
pickover · x · 2026-11-17
A classic cheat sheet from Asimov Institute's Fjodor van Veen and Stefan Leijnen, drawing dozens of neural network architectures on one poster: perceptrons, RNN/LSTM/GRU, autoencoder variants (AE/VAE/DAE/SAE), Boltzmann machines, CNN/DCIGN, GAN, NTM/DNC, capsule networks, attention networks and more.
The authors note that node maps only show structure, not usage: VAEs look like AEs but are generators sampling from noise, while AEs map inputs to their nearest remembered training sample. Abbreviations like RNN and AE are also used inconsistently across the community, often standing in for whole families of architectures.
More from Research
- Motion Synthesis Models Still Demand "A person..." Prompts — Just Rewrite the Captions — andrew_n_carr · 2026-11-17
- Omar Khattab on impactful AI research: invest in projects, not papers — lateinteraction · 2026-11-17
- Coding agents burn two-thirds of tokens after the first edit; upfront plans fix it — rseroter · 2026-11-17
- Apptronik engineer: humanoid whole-body control needs actuator modeling, not just DR — andrew_n_carr · 2026-11-17
- Megakernels dissected: launch overhead, rare compute overlap, and lots of barrier waiting — simran_s_arora · 2026-11-17
- Top AI researcher: embedding audits by METR and Apollo are priced in, mechinterp is the exciting frontier — tszzl · 2026-11-17