Read the equation
Applying softmax to [3,1,0.5,0.1] gives approximately [0.785890,0.106359,0.064510,0.043242]. The source’s [0.73,0.10,0.06,0.04] sums to 0.93 and is not a correctly normalized result. Its qualitative point that finite unmasked logits all receive positive probability is correct, but the displayed numerical example needs correction.
Terms & definitions
| Term | Meaning in this source |
|---|---|
| softmax | Exponentiate each logit and divide by the sum of exponentials |
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
Read the surrounding source passage
π⁰ = Entmax_α(r) where α ∈ (1, 2] Unlike softmax, Entmax produces EXACT ZEROS for low-relevance substrates Softmax([3, 1, 0.5, 0.1]) = [0.73, 0.10, 0.06, 0.04] ← nothing is zero Entmax₂([3, 1, 0.5, 0.1]) = [0.89, 0.11, 0.00, 0.00] ← true sparsity ▼ STAGE 1: MARGIN EMPHASIS
Exact original notation
Softmax([3, 1, 0.5, 0.1]) = [0.73, 0.10, 0.06, 0.04] ← nothing is zero
Related builds
Sources & provenance
Softmax([3, 1, 0.5, 0.1]) = [0.73, 0.10, 0.06, 0.04] ← nothing is zero
Softmax([3, 1, 0.5, 0.1]) = [0.73, 0.10, 0.06, 0.04] ← nothing is zero
Softmax([3, 1, 0.5, 0.1]) = [0.73, 0.10, 0.06, 0.04] ← nothing is zero
Softmax([3, 1, 0.5, 0.1]) = [0.73, 0.10, 0.06, 0.04] ← nothing is zero