Table 3 The architecture of the autoencoder in experiments 1
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 ×4 | LeakyReLu |
Decoder-1 | 4 ×8 | LeakyReLu |
Decoder-2 | 8 ×16 | LeakyReLu |
Decoder-3 | 16 ×32 | LeakyReLu |
Decoder-4 | 32 ×7 | LeakyReLu |
Decoder-Output | 7 | None |