# Broadcasting in loss function for RNN with timeseries
**URL:** https://discourse.julialang.org/t/broadcasting-in-loss-function-for-rnn-with-timeseries/44526
**Category:** Machine Learning
**Created:** [August 7, 2020, 9:34pm UTC](https://discourse.julialang.org/t/broadcasting-in-loss-function-for-rnn-with-timeseries/44526 "2020-08-07T21:34:59Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@raoulg](https://discourse.julialang.org/u/raoulg)
#### Post date: [August 7, 2020, 9:34pm UTC](https://discourse.julialang.org/t/broadcasting-in-loss-function-for-rnn-with-timeseries/44526/1 "2020-08-07T21:34:59Z")
I’m trying to get an RNN to work with timeseries and I don’t understand why things don’t work as expected. I found a workaround, but it just seems to be too complicated.
My data are sequences of 29 observations, and I have 210 observations. With the `chunk` function I got the `(29x210)` matrix reshaped into a 210-element Array `train_x`.
`X = reshape(rand(29*210), (29,210)`
`train_x = chunk(X, 210)`
To get my `y` in the same shape, I apply `chunk` there as well:
`y = chunk(rand(210), 210)`
I created an RNN model `rnn() = Chain(RNN(29,10), Dense(10,1))` that returns a single value. I can now run this as `yhat = m.(train_x)`
This outputs a 210-element Array. So far, so good, I think. Now I’m trying to create a MAE loss function. So, `yhat .- y` works as expected (where I can even ommit the dot). Now I’m trying to apply the `abs` function. I can understand why `abs(yhat .- y)` does not work, but I would have expected `abs.(yhat.-y)` to work. Which it does not…
Well, I can flatten the difference with `...`, but that leaves me with `abs.([((yhat .- y)...)...])` with is both ugly and unreadable. I’m guessing I’m doing something wrong here, but I dont understand why `abs.(yhat.-y)` does not work as expected.
Also, I will want to feed this to `train!` eventually, and I’m not a 100% sure that all these dots will work as expected with the gradients.
questions:
- can someone explain why abs.(yhat .- y) does not work as expected?
- What is the advised way to approach this? Is this approach with all the `...` indeed what is necessary, or is there a more elegant way?
---
### Author:  [@visr](https://discourse.julialang.org/u/visr)
#### Post date: [August 9, 2020, 4:54pm UTC](https://discourse.julialang.org/t/broadcasting-in-loss-function-for-rnn-with-timeseries/44526/2 "2020-08-09T16:54:15Z")
Could it be that you accidentally overwrote `abs` in you session? This should just work:
```julia
julia> a = rand(3);
julia> b = rand(3);
julia> abs.(a - b)
3-element Array{Float64,1}:
0.478177259423227
0.047047520176273006
0.8114939438678288
```
---
### Author:  [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)
#### Post date: [August 9, 2020, 5:30pm UTC](https://discourse.julialang.org/t/broadcasting-in-loss-function-for-rnn-with-timeseries/44526/3 "2020-08-09T17:30:41Z")
You’re in luck, Flux already has a built-in MAE loss: [Loss Functions · Flux](https://fluxml.ai/Flux.jl/stable/models/losses/#Losses-Reference-1)
To add on to @visr’s comment, you’ll also have to clarify what exactly “does not work as expected” means. Is an error being thrown? Are the outputs not what you expected? The gradients? A minimal working example would be much appreciated 🙂
---
### Author:  [@anon92994695](https://discourse.julialang.org/u/anon92994695)
#### Post date: [August 9, 2020, 5:45pm UTC](https://discourse.julialang.org/t/broadcasting-in-loss-function-for-rnn-with-timeseries/44526/4 "2020-08-09T17:45:28Z")
I’m trying to remember - I think a few versions back some loss functions had unexpected type instability. So along those lines upgrade Flux?
Also are you emitting a scalar value for Flux to back prop? I see you mentioning MAE, but I see no sum() or mean() in the offending code?
Error message would be very appreciated 😃
---
### Author:  [@raoulg](https://discourse.julialang.org/u/raoulg)
#### Post date: [September 12, 2020, 10:33pm UTC](https://discourse.julialang.org/t/broadcasting-in-loss-function-for-rnn-with-timeseries/44526/6 "2020-09-12T22:33:55Z")
`abs.(a-b)` works fine, so that is not the problem, so it seems.
The built in MAE loss is exactly what I coded by hand and would expect, eg `agg(abs.(ŷ .- y))`.
I think the problem lies in the shape:
`z = [[1], [2], [3]]`
`abs.(z)`
doesnt work either. The error message is `ERROR: MethodError: no method matching abs(::ARRAY{Int64,1})`
So, I guess will need to remove the extra brackets, somehow flattening the array. Still I’m a bit confused why this is happening in the first place.
A minimal working example is this:
> using Flux: chunk,
> m = Chain(RNN(29,10), Dense(10,1))
> X = reshape(rand(29\*210), (29,210))
> train\_x = chunk(X, 210)
> ŷ = m.(train\_x)
> y = chunk(rand(210), 210)
> abs.(ŷ .- y)