Connecting input and output in keras in this simple XOR problem

Question

I'm trying to recreate this architecture in Keras for solving a XOR problem where there are weights connecting the input (a two-dimensional array) and the output (a scalar). I know that the XOR problem can be solved using a fully connected 2,2,1 architecture, but I don't know how to implement this architecture in Keras.

I read the docs and researched SO but I can't seem to find a solution. The following code shows what I have done so far. My main issue is how to connect the hidden layer and the output layer.

input1 = keras.layers.Input(shape=(2,)) # input
hidden_layer = keras.layers.Dense(1, activation='tanh')(input1) # linking the input with the hidden layer
output1 = keras.layers.Dense(1, activation='tanh')(input1) # linking the input with the output layer
# The code for connecting hidden and output layer should probably go here #
model = keras.models.Model(inputs=input1, outputs=outpu1) 
model.compile(...)

Answer 1

Hi Evelyn welcome to stacckoverflow.

I think that it makes more sense to do it with two inputs.

You can implement it as follows:

import tensorflow as tf
from tensorflow import keras


inp1 = keras.layers.Input(shape=(1,))
inp2 = keras.layers.Input(shape=(1,))

x = keras.layers.Concatenate()([inp1, inp2])
x = keras.layers.Dense(1, activation='tanh')(x)

x = keras.layers.Concatenate()([inp1, inp2, x])
output = keras.layers.Dense(1, activation='tanh')(x)

model = keras.models.Model(inputs=[inp1, inp2], outputs=output) 
model.summary()
model([tf.ones([8, 1]), tf.zeros([8, 1])])