Gaussian error linear unit

Read the equation

GELU multiplies x by the standard normal cumulative probability at x. The function implements it with erf, giving a smooth activation that attenuates many negative values and approaches x for large positive values. The Φ in this formula is a Gaussian CDF, not the project’s unity score or an IIT quantity.

Terms & definitions

How it works

Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.

Assumptions & limits

Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.

Original context

		result[i] = (v-mean)/std*gamma + beta
	}

	return result
}

// GELU computes Gaussian Error Linear Unit
// GELU(x) = x · Φ(x) where Φ is the CDF of N(0,1)
func GELU(x float64) float64 {
	return 0.5 * x * (1.0 + math.Erf(x/math.Sqrt(2.0)))
}

// SwiGLU computes SwiGLU activation
// SwiGLU(x, W, V, b, c) = Swish(xW + b) ⊗ (xV + c)
func SwiGLU(x []float64, gate, linear []float64) []float64 {
	n := len(x)
	if n == 0 || len(gate) != n || len(linear) != n {
		return x

GELU(x) = x · Φ(x) where Φ is the CDF of N(0,1)

Related builds