0
$\begingroup$

I have the following setup:

  • 2 input neurons (I1, I2)
  • 2 output neurons (O1, O2)
  • 1 hidden layer with 3 neurons (H1, H2, H3)
  • loss function = mse
  • optimizer = Adam
  • the values from I1 range from 0 - 100
  • the values from I2 range from 0 - 500
  • batch size = 16
  • learning rate = 0.1

The ANN should learn the following rules (regression problem):

  1. If I1 increasing O1 decreasing
  2. If I1 increasing O2 increasing
  3. If I2 increasing O1 constant
  4. If I2 increasing O1 decreasing

I am using the following model:

class DQN(nn.Module):
    def __init__(self):
        super().__init__()

        self.fc1 = nn.Linear(in_features=2, out_features=3)
        self.out = nn.Linear(in_features=3, out_features=2)

    def forward(self, t):
        t = F.relu(self.fc1(t))
        t = self.out(t)
        return t

However, it does not learn. My question is, which part should I focus on? Is a linear, fully connected network maybe not suitable for the rules (no linear regression)? Do I need more hidden layers / more neurons? Is the learning rate a problem? Should the input data be normalized?

I tinkered around a lot, but didn't get any improvements.

$\endgroup$
3
  • $\begingroup$ Although the suggested duplicate is classification using Torch, it is the exact same problem, and a common beginner's problem. $\endgroup$ Feb 13 at 12:45
  • $\begingroup$ As you suggested, I normalized I1 with value / 100 and I2 with value / 500. So I always have values between 0-1. Unfortunately, the improvement is very limited. $\endgroup$
    – Steve2Fish
    Feb 14 at 19:25
  • $\begingroup$ Sorry, that looked like a clear problem to me. It seems the code, deign or data have other problems too. $\endgroup$ Feb 14 at 20:22

1 Answer 1

0
$\begingroup$

The learning rate is too high. Make it between 0.001 and 0.0001. It's also possible that your hidden layer may not have modeled the relationship well. Try doubling/incrementing the neurons in the hidden layer like 4, 8, 12, 16, and then chose the appropriate one.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.