Description
Return max(left,right), leftActive when left>=right and rightActive when right>=left.
A two-value maxout operation chooses the larger input. When both inputs are equal, both attain the maximum; identifying that tie does not choose how an autodifferentiation system should distribute a gradient.
Return max(left,right), leftActive when left>=right and rightActive when right>=left.
When to use this tool
Use Activation: Maxout Two Value Tie Mask when checking the stated two-input maximum and tie convention.
How to use the tool and how it works
- Enter left, right. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read result. Expand result to inspect the returned fields.
Return max(left,right), leftActive when left>=right and rightActive when right>=left. tie means exact equality, so both activity flags are true on a tie.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| left | Left | Required. Finite number. |
| right | Right | Required. Finite number. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| result | Object containing the operation-specific returned members listed below. | Required. Object. |
| result.maximum | Maximum | Calculated result member: number. |
| result.leftActive | Left Active | Calculated result member: boolean. |
| result.rightActive | Right Active | Calculated result member: boolean. |
| result.tie | Exact equality; both activity flags are true on a tie without allocating gradient weights. | Calculated result member: boolean. |
{
"input": {
"left": 2,
"right": 2
},
"output": {
"result": {
"maximum": 2,
"leftActive": true,
"rightActive": true,
"tie": true
}
}
}Limitations and assumptions
- Activity flags do not choose a unique derivative, split gradient weight or apply an approximate tie tolerance.
- 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
Similar or alternative tools
- ReLU Zero Subgradient Choice
Return slope one for positive x, zero for negative x and the supplied slope at zero; flag x=0 as nondifferentiable.
- Activation: Leaky ReLU Scalar Inverse
For positive slope return one inverse, y when y>=0 otherwise y/slope.