andy
b30da1d29c
Affected files: .obsidian/graph.json .obsidian/workspace.json Money/Assets/Derivative.md STEM/AI/Neural Networks/CNN/Examples.md STEM/AI/Neural Networks/Deep Learning.md STEM/AI/Neural Networks/MLP/Decision Boundary.md STEM/CS/Languages/dotNet.md STEM/Semiconductors/Equations.md Tattoo/Engineering.md
43 lines
905 B
Markdown
43 lines
905 B
Markdown
# LeNet
|
|
- 1990's
|
|
|
|
- 1989
|
|
|
|
- 1998
|
|
|
|
# AlexNet
|
|
2012
|
|
|
|
- [[Activation Functions#ReLu|ReLu]]
|
|
- Normalisation
|
|
|
|
|
|
|
|
# VGG
|
|
2015
|
|
|
|
- 16 layers over AlexNet's 8
|
|
- Looking at vanishing gradient problem
|
|
- Xavier
|
|
- Similar kernel size throughout
|
|
- Gradual filter increase
|
|
|
|
|
|
|
|
|
|
# GoogLeNet
|
|
2015
|
|
|
|
- [[Inception Layer]]s
|
|
- Multiple [[Deep Learning#Loss Function|Loss]] Functions
|
|
|
|
|
|
|
|
## [[Inception Layer]]
|
|
|
|
## Auxiliary [[Deep Learning#Loss Function|Loss]] Functions
|
|
- Two other SoftMax blocks
|
|
- Help train really deep network
|
|
- Vanishing gradient problem
|
|
|
|
 |