Research Article
DC-NNMN: Across Components Fault Diagnosis Based on Deep Few-Shot Learning
| Algorithm: deep convolution near neighbor matching networks | , , , is the number of query set |
| Require:: Distribution over tasks | Require:: step size hyperparameters | (1) randomly initialize | (2) while not done do | (3) Sample batch of tasks | (4) for all t do | (5) Evaluate with respect to examples | (6) Compute adapted parameters with Adam: | | | | (7) end for | (8) Update: | | Adam () | (9) end while |
|
|