I must be idiot but I can’t realise how to do very basic… no Convolution, RNN, gates,… just a basic plain feed-forward neural network design/testing/validation in Flux. Somethink like: l1 = FullyConnectedLayer(tanh,2,3,w=ones(3,2), wb=zeros(3)) l2 = FullyConnectedLayer(tanh,3,2, w=ones(2,3), wb=ze…

[image] sylvaticus: using Flux xtrain = [0.1 0.2; 0.3 0.5; 0.4 0.1; 0.5 0.4; 0.7 0.9; 0.2 0.1] ytrain = [0.3; 0.8; 0.5; 0.9; 1.6; 0.3] xtest = [0.5 0.6; 0.14 0.2; 0.3 0.7] ytest = [1.1; 0.36; 1.0] # Direct way. Error: “Output should be scalar”: model = Chain(Dense(2, 1)) loss(x, y) = Flux.mse,(m…

How to train/predict a very simple feed-forward neural network in Flux?

Specific Domains Machine Learning

Albert_Zevelev May 16, 2020, 3:19am 3

@sylvaticus maybe my code will help:
Generic Function to train NN w/ Flux

Topic		Replies	Views
Question about how to train a neural network using Flux.jl Machine Learning first-steps , flux	1	2337	October 8, 2018
A package/example for a simple neural network? Machine Learning question	4	1242	July 17, 2020
Problems with Flux NN regression Machine Learning question , package	1	404	November 19, 2021
Flux.jl: Initializing Parameters in Specified Range Machine Learning	1	913	July 10, 2020
Unstable learning of neural net with few nodes using Flux Machine Learning flux	9	574	November 28, 2021

How to train/predict a very simple feed-forward neural network in Flux?

Related topics