non linear regression solving xor function using a neural network with no hidden layers Artificial Intelligence Stack Exchange
We have considered three different cases having 103, 104, and 106 samples in the dataset, respectively. Results (in all three cases) have been summarized in Table 2. Results show that the loss depends upon the no. of samples in the dataset. Furthermore, we would expect the gradients to all approach zero. Real world problems require…
Citește mai mult