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	2339	October 8, 2018
Flux function fitting Machine Learning flux	2	1048	August 7, 2020
Flux results not similar to Tensorflow Machine Learning question	3	1817	March 11, 2019
Generic Function to train NN w/ Flux Machine Learning flux	7	1648	April 14, 2020
Problems with Flux Machine Learning	2	1596	March 14, 2018

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

Related topics