# Question about how to train a neural network using Flux.jl

**URL:** <https://discourse.julialang.org/t/question-about-how-to-train-a-neural-network-using-flux-jl/16011>\
**Category:** Machine Learning\
**Tags:** first-steps, flux\
**Created:** [October 8, 2018, 6:49am UTC](https://discourse.julialang.org/t/question-about-how-to-train-a-neural-network-using-flux-jl/16011 "2018-10-08T06:49:08Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![xiaodai](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/xiaodai/32/15937_2.png) [@xiaodai](https://discourse.julialang.org/u/xiaodai)\
**Post date:** [October 8, 2018, 6:49am UTC](https://discourse.julialang.org/t/question-about-how-to-train-a-neural-network-using-flux-jl/16011/1 "2018-10-08T06:49:08Z")

</div>

I am trying to build a neural network that has about 200 Boolean features as inputs and I would like to train it against a regression output (so the `y` is continuous). I tried to setup the network like so

```julia
using Flux
model = Flux.Chain(
  Dense(14*16+4, 64, relu),
    Dense(64, 16, relu),
    Dense(16, 1, relu));

```

so I got 3 dense layers all activated by `relu` and now to test my understanding I just ran the `x` through the model

```julia
x = rand(Bool, 14*16+4)
model(x)

```

so far so good but the below gives error

```julia
y = 100
loss(x,y) = (model(x) - y)^2

Flux.train!(loss, [(x,y)])
# Flux.train!(loss, [(x,y)], ADAM(...)) # this didn't work either

```

and the error is

> MethodError: no method matching train!(::typeof(loss), ::Array{Tuple{Array{Bool,2},Array{Float64,1}},1})  
> Closest candidates are:  
> train!(::Any, ::Any, !Matched::Any; cb) at /home/jrun/.julia/packages/Flux/UHjNa/src/optimise/train.jl:56
> 
> Stacktrace:  
> [1] top-level scope at In[106]:1

This is after having browsed through the model zoo and I can’t seem to figure out how to do this simple neural network. I am doing a simple prototype of reinforcement learning, so being able to update the model is also important so would appreciate pointers to `Flux.train!` and `Flux.update!` and how to make them work

---

<div class="post-metadata">

**Author:** ![kdyrhage](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/kdyrhage/32/2326_2.png) [@kdyrhage](https://discourse.julialang.org/u/kdyrhage)\
**Post date:** [October 8, 2018, 10:01am UTC](https://discourse.julialang.org/t/question-about-how-to-train-a-neural-network-using-flux-jl/16011/2 "2018-10-08T10:01:09Z")

</div>

`loss(x,y)` needs to return a scalar:

```julia
using Flux
model = Flux.Chain(
    Dense(14*16+4, 64, relu),
    Dense(64, 16, relu),
    Dense(16, 1, relu));
x = rand(Bool, 14*16+4)
y = 100
loss(x,y) = sum((model(x) .- y).^2)
opt = ADAM(params(model))
Flux.@epochs 100 Flux.train!(loss, [(x,y)], opt)

```