I have a feedforward neural network with 3 hidden layers. I train it with a data that is not standardized and it have accuracy of 90% on the test data. Then I normalize the data and the accuracy of the model decreases to 55%? (I expected it to be increased)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2)
# Standardization
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
Why is this happening and how can I increase the performance of such a model?
