Skip to content

Instantly share code, notes, and snippets.

@MattSkiff

MattSkiff/neural_network_architectures_diagram.R

Last active March 15, 2020 11:51
Show Gist options
  • Save MattSkiff/b831f217df9756ec4179117a3cf487e2 to your computer and use it in GitHub Desktop.
Save MattSkiff/b831f217df9756ec4179117a3cf487e2 to your computer and use it in GitHub Desktop.
Download ZIP
Example of simple flowchart using diagrammeR. Content: highly subjective! (from a shallow literature dive)
Raw
neural_network_architectures_diagram.R
library(DiagrammeR)
gr <-grViz("digraph flowchart {
# node definitions with substituted label text
node [fontname = Helvetica, shape = rectangle]
# edge definitions with the node IDs
'Linear Combiner (Perceptron) (ANN)' -> 'Multiple Linear Combiner (One Layer Perceptron)';
'Multiple Linear Combiner (One Layer Perceptron)'-> 'MLP (FFNN)'
'MLP (FFNN)' -> 'RBF-NN';
'Neocognitron' -> 'LeNet'-> 'AlexNet (DCNNs)';
'AlexNet (DCNNs)' -> 'DeepFace';
'AlexNet (DCNNs)' -> 'VGG';
'AlexNet (DCNNs)' -> 'Inception Net';
'AlexNet (DCNNs)' -> 'ResNet';
'AlexNet (DCNNs)' -> 'R-CNN' -> 'Fast R-CNN';
'AlexNet (DCNNs)' -> 'YOLO';
'AlexNet (DCNNs)' -> 'SqueezeNet';
'LeNet' -> 'GNN' -> 'GTN' -> 'GPT-2';
'GTN' -> 'BERT';
'MLP (FFNN)' -> 'ELM';
'MLP (FFNN)' -> 'SNN';
'MLP (FFNN)' -> 'SOM (CNNs)';
'MLP (FFNN)' -> 'Autoencoders' -> 'DAE' -> 'VAE';
'MLP (FFNN)' -> 'TDNN';
'TDNN' -> 'RNNs' -> 'BRNN';
'RNNs' -> 'LTSM';
'SOM (CNNs)' -> 'Neocognitron'
'MLP (FFNN)' -> 'Hopfield Nets' -> 'RNNs';
'DBM' -> 'GSN';
'MLP (FFNN)' -> 'Boltzmann Machine' -> 'RBM' -> 'DBM';
'GSN' -> 'GAN' -> 'GauGAN';
'GAN' -> 'StyleGAN';
}
")
gr
# RBF: https://apps.dtic.mil/docs/citations/ADA196234
# GauGAN: https://www.researchgate.net/publication/334714551_GauGAN_semantic_image_synthesis_with_spatially_adaptive_normalization
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment