# Neural network is not giving the expected output after training in Python

My neural network is not giving the expected output after training in Python. Is there any error in the code? Is there any way to reduce the mean squared error (MSE)?

I tried to train (Run the program) the network repeatedly but it is not learning, instead it is giving the same MSE and output.

Here is the Data I used:

Here is my code:

#load and evaluate a saved model

# summarize model.
model.summary()
#Model starts
import numpy as np
import pandas as pd
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.models import Sequential
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
# Importing the dataset

# Splitting the dataset into the Training set and Test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.08, random_state = 0)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# Initialising the ANN
model = Sequential()

# Adding the input layer and the first hidden layer
model.add(Dense(32, activation = 'tanh', input_dim = 4))

# Adding the second hidden layer
model.add(Dense(units = 18, activation = 'tanh'))

# Adding the third hidden layer
model.add(Dense(units = 32, activation = 'tanh'))

# Compiling the ANN
model.compile(optimizer = 'adam', loss = 'mean_squared_error')

# Fitting the ANN to the Training set
model.fit(X_train, y_train, batch_size = 100, epochs = 1000)

y_pred = model.predict(X_test)
for i in range(5):
print('%s => %d (expected %s)' % (X[i].tolist(), y_pred[i], y[i].tolist()))

plt.plot(y_test, color = 'red', label = 'Test data')
plt.plot(y_pred, color = 'blue', label = 'Predicted data')
plt.title('Prediction')
plt.legend()
plt.show()

# save model and architecture to single file
model.save("ANNnew.h5")
print("Saved model to disk")


• It seems to me your case could fall as ordinal regression. Have you tried training it as classification model? It might sound weird but people did it and it worked sometime. – Yohanes Alfredo Nov 22 '19 at 17:33
• @YohanesAlfredo I did not tried training it as classification model.. My I know how to do that? please elaborate. – VASIH Nov 22 '19 at 17:41
• I mean it is simple. you just modify it to output probabilities of each classes, and use crossentropy loss instead – Yohanes Alfredo Nov 22 '19 at 18:03