Can there be negative weights in neural networks?

Question

Neural networks

When adjusting the weights in the neural network, one of the weights became negative. I use the activation function of the logistic function. Can the weights in neural networks be negative?

Answer 1

Certainly.
Imagine that one of the neurons in the first layer has a positive weight.
Now imagine that its input signal was multiplied by -1 (well, just some kind of sensor was connected the other way around).
What will happen to the weight after retraining?