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.

Original post →

More from Research

Research channel →