In the Flux docs for train! it says In case datapoints d are of numeric array type, assume no splatting is needed and compute the gradient of loss(d) . What does “splatting” mean here? I am guessing that what this means is that, if the data are expressed as matrices (dimensions X datapoints) …

What is "splatting" in flux (loss?)?

Tamas_Papp April 14, 2020, 6:16am 2

It may not be specific to Flux, just the splat operator ....

Topic		Replies	Views
What datatypes can you pass into train! Machine Learning	3	447	June 18, 2019
Lux (And Flux), "parallel" Network Input. When Input is flat, Zygote gradient works, when input is not flat it doesn't Machine Learning flux , zygote , lux	10	728	February 5, 2024
Specifying loss functions in Flux.jl Machine Learning question , package , flux	8	1971	August 8, 2020
Data-formatting in and out of Flux ML model Machine Learning	1	446	July 28, 2021
Broadcasting over a Flux.DataLoader Machine Learning	11	1609	November 4, 2021