andy
4cc2e79866
Affected files: .obsidian/global-search.json .obsidian/workspace.json Health/Alexithymia.md Health/BWS.md STEM/AI/Neural Networks/Activation Functions.md STEM/AI/Neural Networks/Architectures.md STEM/AI/Neural Networks/CNN/CNN.md STEM/AI/Neural Networks/MLP/Back-Propagation.md STEM/AI/Neural Networks/Transformers/Attention.md STEM/CS/Calling Conventions.md STEM/CS/Languages/Assembly.md |
||
---|---|---|
.. | ||
Back-Propagation.md | ||
Decision Boundary.md | ||
MLP.md | ||
README.md |
- Architectures
- Single hidden layer can learn any function
- Universal approximation theorem
- Each hidden layer can operate as a different feature extraction layer
- Lots of Weight Init to learn
- Back-Propagation is supervised
Universal Approximation Theory
A finite Architectures MLP with 1 hidden layer can in theory approximate any mathematical function
- In practice not trainable with Back-Propagation
Weight Matrix
- Use matrix multiplication for layer output
- TLU is hard limiter !
o_1
too_4
must all be one to overcome -3.5 bias and force output to 1 !- Can generate a non-linear Decision Boundary