Model Accuracy for Non-linear Relationship with Logarithm Kernel and Exponential Activation can’t reach 100%
I’m working on a project where I need to model a non-linear relationship using a neural network. The relationship is ( y = 3x_1^2x_2^3 ). The network setup is as follows:
Why is my DNN model failing to learn the product of two inputs despite logarithmic preprocessing and an exponential activation function?
I’m working on a project involving a feedforward deep neural network (DNN) designed to learn the product of two input values. Theoretically, this should be straightforward, especially with the preprocessing and activation functions I’ve employed. However, the model fails to find the correct weights and biases, resulting in high errors during both interpolation and extrapolation.