I want to estimate F in this equation using a Dense neural network. Y = F(X) @ U. F is a 3x3 matrix, U, X and Y are 3x1 vectors. I create following network,
from keras.models import Sequential
from keras.layers import Dense
from tensorflow.keras.optimizers import SGD
from keras import backend as K
import numpy as np
def define_model(lr=0.01):
model = Sequential()
model.add(Dense(20, input_dim=3))
model.add(Dense(9 ) )
# compile model
opt = SGD(learning_rate=lr, momentum=0.0)
model.compile(optimizer=opt, loss='mse', metrics=['accuracy'])
return model
But I don't know how to train this network. Please help me.
