Table 5 Architecture parameters of the model for experiment 2
From: CLeaR: An adaptive continual learning framework for regression tasks
Layer | Size | Activation |
|---|---|---|
Encoder-Input | 7 | None |
Encoder-1 | 7 ×32 | LeakyReLu |
Encoder-2 | 32 ×16 | LeakyReLu |
Encoder-3 | 16 ×8 | LeakyReLu |
Encoder-4 | 8 ×Latent size | LeakyReLu |
Decoder-1 | Latent size ×8 | LeakyReLu |
Decoder-2 | 8 ×16 | LeakyReLu |
Decoder-3 | 16 ×32 | LeakyReLu |
Decoder-4 | 32 ×7 | LeakyReLu |
Decoder-Output | 7 | None |
DNN-1 | Latent size ×96 | Tanh |
DNN-2 | 96 ×64 | Tanh |
DNN-3 | 64 ×32 | Tanh |
DNN-4 | 32 ×16 | Tanh |
DNN-5 | 16 ×8 | Tanh |
DNN-Output | 8 ×1 | None |