normalise(x; dims=ndims(x), eps=1e-5)

Normalise x to mean 0 and standard deviation 1 across the dimension(s) given by dims. Per default, dims is the last dimension. eps is a small term added to the denominator for numerical stability.

Examples

			julia> using Statistics

julia> x = [90, 100, 110, 130, 70];

julia> mean(x), std(x; corrected=false)
(100.0, 20.0)

julia> y = Flux.normalise(x)
5-element Vector{Float64}:
 -0.49999975000012503
  0.0
  0.49999975000012503
  1.499999250000375
 -1.499999250000375

julia> isapprox(std(y; corrected=false), 1, atol=1e-5)
true

julia> x = rand(10:100, 10, 10);

julia> y = Flux.normalise(x, dims=1);

julia> isapprox(std(y; dims=1, corrected=false), ones(1, 10), atol=1e-5)
true