Skip to content

Main content

Activation: Softsign Scalar Inverse Tool

Invert scalar softsign y=x/(1+abs(x)) only inside its open range (-1,1).

Loading tool…

Description

Invert softsign x/(1+abs(x)) as x=y/(1-abs(y)).

Softsign uses x/(1+abs(x)); its finite-input range is between -1 and 1. It has a first derivative at zero but different one-sided second derivatives there. Changing an additive denominator scale is distinct from multiplying the function’s input by a scale.

Invert softsign x/(1+abs(x)) as x=y/(1-abs(y)).

When to use this tool

Use Activation: Softsign Scalar Inverse when checking the stated softsign inverse, saturation or derivative convention.

How to use the tool and how it works

  1. Enter y. Use the units and conventions below.
  2. Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
  3. Read result. Expand result to inspect the returned fields.

Require abs(y)<1. Invert softsign x/(1+abs(x)) as x=y/(1-abs(y)).1

Input fieldMeaning and unitsAccepted input
yYRequired. Finite number.
Output fieldInterpretationReturned shape
resultObject containing the operation-specific returned members listed below.Required. Object.
result.xFinite scalar input coordinate; use the mathematical scale specified above.Calculated result member: number.
json
{
  "input": {
    "y": 0.5
  },
  "output": {
    "result": {
      "x": 1
    }
  }
}

Limitations and assumptions

  • Output limits ±1 have no finite preimage; floating-point inversion near those limits can be very sensitive.
  • Outputs are nested inside result. Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
  • Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.

Alternative or Complementary methods

Use the complete explicit function and the intended parameter, branch and numerical conventions for symbolic, tensor or model-level differentiation; assess training behavior independently.

References

  1. Calculation and input contract: activation/softsign-scalar-inverse — tool.io

Similar or alternative tools