silu

std.elementwise.silu · Level L0

SiLU (also called swish): x times its own sigmoid.

x·σ(x)

Signature

silu(x: f64[n]) → f64[n]

Structure

The function as NOVA stores it: one box per input, operation and output, and arrows that carry values. A double border marks another library function this one runs — called once, or by Scan once per element; select it to open that function.

xf64[n]SigmoidgateMultiplyyyf64[n]
  • input
  • operation
  • constant
  • call
  • output

Verification

  • Signature proven by NOVA’s shape solver, for every size.
  • Agrees with the reference x / (1 + np.exp(-x)) to 80 digits (100-digit arithmetic), on all 40 test cases.
  • All 162 float64 results inside the running error bound; the closest uses 17% of it.
  • Interpreter and NumPy backend return bit-identical results.
Accuracy in detail
correctly rounded (the float64 nearest the exact value)
59%
bit-equal to the NumPy formula in float64
83%
largest error, in units in the last place
1.72

Identity

Calls
—
Called by
—
sha256:a4869515e283f2a1932bee4529de2e531e46a04e17f20bc21fbca8d036e4b112

The semantic hash of the graph. It changes when the program changes, and never when only its documentation does.

Control handle

Symbol
Ω:std.elementwise.silu · Ω:silu
Pins
sha256:2445e75ce5fa3e3d19ee1ccfe1df7ea56f6bcc2f5584196d5d50a8543cff92dathis graph alone
Evidence
sha256:09fb2b5122328c434c5242a587a1fdae71f94ee427362ba35bcbcb353bcf879ethe hash of its verification record
Needs
no capability: a pure function

Through NOVA’s control layer, the symbol launches this function only while the program still matches what it pins: a change to this graph, or to any graph it reaches, needs a migration first.