《深度學習——Andrew Ng》第一課第四周程式設計作業
阿新 • • 發佈:2019-01-09
Building your Deep Neural Network: Step by Step
3.2 - L-layer Neural Network
The initialization for a deeper L-layer neural network is more complicated because there are many more weight matrices and bias vectors. When completing the initialize_parameters_deep
, you should make sure that your dimensions match between each layer. Recall that is the number of units in layer . Thus for example if the size of our input is (with examples) then:
**Shape of W** | **Shape of b** | **Activation** | **Shape of Activation** | |
**Layer 1** | ||||
**Layer 2** | ||||
**Layer L-1** | ||||
**Layer L** |