Simple XOR learning with keras

xor.py

from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
import numpy as np 

X = np.array([[0,0],[0,1],[1,0],[1,1]])
y = np.array([[0],[1],[1],[0]])

model = Sequential()
model.add(Dense(8, input_dim=2))
model.add(Activation('tanh'))
model.add(Dense(1))
model.add(Activation('sigmoid'))

sgd = SGD(lr=0.1)
model.compile(loss='binary_crossentropy', optimizer=sgd)

model.fit(X, y, show_accuracy=True, batch_size=1, nb_epoch=1000)
print(model.predict_proba(X))
"""
[[ 0.0033028 ]
 [ 0.99581173]
 [ 0.99530098]
 [ 0.00564186]]
"""

I wanted to solve this with only two hidden units. So I used this code which worked fine (for most executions, depending on the random initial condition):

 from keras.models import Sequential
 from keras.layers.core import Dense, Dropout, Activation
 from keras.optimizers import SGD
 import numpy as np
 
 X = np.array([[0,0],[0,1],[1,0],[1,1]])
 y = np.array([[0],[1],[1],[0]])
 
 model = Sequential()
 model.add(Dense(2, input_dim=2))
 model.add(Activation('tanh'))
 model.add(Dense(1))
 model.add(Activation('sigmoid'))
 
 sgd = SGD(lr=0.1)
 model.compile(loss='mean_squared_error', optimizer=sgd)
 
 model.fit(X, y, batch_size=1, epochs=1000)
 print(model.predict_proba(X))

I think to solve it for any initial condition we need to have scattered inputs like @baj12 proposed. But I didn't test it.

I added some biases and random initialization as well, however I have no better result as consciencia

rndU = RandomUniform(minval=-1, maxval=1, seed=None)
model = Sequential()
model.add(Dense(9, activation='sigmoid', input_dim=2, use_bias = True, kernel_initializer=rndU, bias_initializer=rndU))
model.add(Dense(1, activation='sigmoid', use_bias = True, kernel_initializer=rndU, bias_initializer=rndU))

from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
from keras.initializers import RandomUniform
import numpy as np
x=np.array([[0.1,0.1,1],
[0.1,0.9,1],
[0.9,0.1,1],
[0.9,0.9,1]])
y=np.array([[0.1],[0.9],[0.9],[0.1]])
model= Sequential()
model.add(Dense(4,input_dim=3,activation="sigmoid",
bias_initializer=RandomUniform(minval=-1.0, maxval=1, seed=None)))
model.add(Dense(1,activation="sigmoid",bias_initializer=RandomUniform(minval=-1.0, maxval=1, seed=None)))
sgd=SGD(lr=0.01)
model.compile(loss='mean_squared_error',optimizer='sgd')
model.fit(x,y,epochs=5000,batch_size=1,verbose=1)

i am not geeting good result what i am doing wrong any idea

@gauravkr0071 replace
model.compile(loss='mean_squared_error',optimizer='sgd')
by this
model.compile(loss='mean_squared_error',optimizer=sgd)

reattacking this problem (with the guidance of o1/chatGPT):
https://github.com/baj12/XOR