2023-05-27 00:50:46 +01:00
|
|
|
# Single-Layer Feedforward
|
|
|
|
|
- *Acyclic*
|
|
|
|
|
- Count output layer, no computation at input
|
|
|
|
|
|
2023-05-31 22:21:56 +01:00
|
|
|
|
2023-05-27 00:50:46 +01:00
|
|
|
|
|
|
|
|
# Multilayer Feedforward
|
|
|
|
|
- Hidden layers
|
|
|
|
|
- Extract higher-order statistics
|
|
|
|
|
- Global perspective
|
|
|
|
|
- Helpful with large input layer
|
|
|
|
|
- Fully connected
|
|
|
|
|
- Every neuron is connected to every neuron adjacent layers
|
|
|
|
|
- Below is a 10-4-2 network
|
2023-05-31 22:21:56 +01:00
|
|
|
|
2023-05-27 00:50:46 +01:00
|
|
|
|
|
|
|
|
# Recurrent
|
|
|
|
|
- At least one feedback loop
|
|
|
|
|
- Below has no self-feedback
|
2023-05-31 22:21:56 +01:00
|
|
|
|
|
|
|
|
|
2023-05-27 00:50:46 +01:00
|
|
|
|
|
|
|
|
- Above has hidden neurons
|
