= Jamie Ryan Kiros
{c}
<Jamie Ryan Kiros> coauthored the 2016 <layer normalization> paper with <Jimmy Lei Ba> and <Geoffrey E. Hinton>. The original paper gives the full byline Jamie Ryan Kiros and a University of Toronto affiliation. Its normalization statistics are computed across the inputs within one case, rather than across different cases in a batch.<Layer Normalization by Jimmy Lei Ba and others>[Title page; §3, equation 3; §3.1, recurrent-network application]{ref}
A small original implementation experiment tests that distinction without measuring training speed. Fix one case's two inputs at $h=(2,6)$, unit gains, zero biases and a variance stabilizer of $1$. The within-case mean is $4$ and variance is $4$, so its normalized outputs are
$$
\frac{h-4}{\sqrt{4+1}}=\left(-\frac{2}{\sqrt5},\frac{2}{\sqrt5}\right)\approx(-0.8944,0.8944).
$$
Evaluate this case first beside another case $(-100,100)$ and then beside $(1000,2000)$. The stated isolated normalization computation returns the same output for $h$ in both evaluations, because neither companion enters its statistics. This tests a concrete dependency of the computation, not a claim about every layer of a complete network.
The paper also studies <recurrent neural networks>, computing the statistics separately at each time step.<Layer Normalization by Jimmy Lei Ba and others>[§3.1 and experimental sections]{ref} That application makes the choice of averaging axes consequential. The paper establishes a collaborative contribution; its byline does not assign a separate invention to each author.
Back to article page
