from keras.models import Sequential
from keras.layers import Dense, Activation
 
model = Sequential([
    Dense(32, input_dim=784),
    Activation('relu'),
    Dense(10),
    Activation('softmax'),
])

ZnJvbSBrZXJhcy5tb2RlbHMgaW1wb3J0IFNlcXVlbnRpYWwKZnJvbSBrZXJhcy5sYXllcnMgaW1wb3J0IERlbnNlLCBBY3RpdmF0aW9uCgptb2RlbCA9IFNlcXVlbnRpYWwoWwogICAgRGVuc2UoMzIsIGlucHV0X2RpbT03ODQpLAogICAgQWN0aXZhdGlvbigncmVsdScpLAogICAgRGVuc2UoMTApLAogICAgQWN0aXZhdGlvbignc29mdG1heCcpLApdKQ==

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

import numpy as np 
from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense  
def generate_data(samples=1000):  
  x1 = np.random.rand(samples)  
  x2 = np.random.rand(samples)  
  y = x1 + x2  
return np.vstack((x1, x2)).T, y  
x_train, y_train = generate_data(10000) 
x_val, y_val = generate_data(1000) 
model = Sequential() 
model.add(Dense(8, input_dim=2,activation='relu')) model.add(Dense(1)) model.compile(optimizer='adam', loss='mean_squared_error')  
model.fit(x_train, y_train, epochs=100, batch_size=32, validation_data=(x_val, y_val))  x_test, y_test = generate_data(10) 
predictions = model.predict(x_test)  
for i in range(len(x_test)):  
  print(f"Input: {x_test[i]}, Predicted Sum: {predictions[i][0]}, Actual Sum: {y_test[i]}")