XOR Model is very bad - what am I doing wrong?

[KFrank]

Hi Dr. Noob!

@AbsolutePytorchNoob

I’m training a simple XOR neural network

		self.fc1 = nn.Linear(2,2)
		self.fc2 = nn.Linear(2,1)

You have a “hidden layer” with two “neurons.” I believe that this
does not have enough structure to capture XOR (and the quadratic
term embedded in it). Try adding a third hidden neuron:

		self.fc1 = nn.Linear (2, 3)
		self.fc2 = nn.Linear (3 ,1)

Please see this related post for some additional explanation:

Simple pattern is not detected by simple linear model

I have a very simple example of 6 training data with 6 labels. I am trying to fit a simple logistic regression to it, and hoping it should over-fit with 0 loss, but the model does not converge. Here is the rule, i am hoping the model to learn: When input is [1., 0., 0., 1.] , the label is 1 When input is [0., 1., 1., 0.] , the label is 1 When input is [1., 0., 1., 0.] , the label is 0 When input is [0., 1., 0., 1.] , the label is 0 is such pattern something a non-linear model cannot capt…

Best.

K. Frank