Checks / pattern
Sigmoid / Tanh in deep networks
Check R11. Runs in the editor as you build, in CI through the
GitHub Action, and over the wire at
POST /api/v1/check. Milliseconds, before any GPU is billed.
info
pattern
R11
| Trigger | Sigmoid or Tanh activation appears in a network with ≥ 5 weight-carrying layers. |
|---|---|
| Why | Saturating activations vanish gradients in deep stacks. ReLU / GELU / SiLU are the modern defaults. |
| Source | Glorot & Bengio 2010 on the vanishing gradient problem. |
Why it is not a lint you can ignore
A structural mistake does not fail at review time and it does not fail at import
time. It fails when the module is constructed on the training node, after the job was queued and
the dataset was downloaded. That is why this runs before the spend and not after it.
Run this check on your own model
Free, no account needed
Every check
41 structural checks: 6 guardrail gates and 35 architecture advisor rules. See the full catalogue.
← R10 Attention without positional encoding ยท R12 Deep network with no normalization →