accuracy of keras is not improving

Question

I am comparing Keras with Random forest. I follow research paper and it give keras model is high accuracy as compare to random forest model, but when i implemented it not give me. Accuracy and STD of RF* 0.997 0.0006 Accuracy of Keras 0.0079

#Importing dataset 
    dataset = pd.read_csv('KDD_Dataset.csv')
    X = dataset.iloc[:, :-1].values
    y = dataset.iloc[:, 41:42].values

    from sklearn.preprocessing import LabelEncoder
    labelencoder_X = LabelEncoder()
    X[:,0] = labelencoder_X.fit_transform(X[:,0])
    X[:,1] = labelencoder_X.fit_transform(X[:,1])
    X[:,2] = labelencoder_X.fit_transform(X[:,2])
    #
    from sklearn.preprocessing import OneHotEncoder
    onehotencoder_0 = OneHotEncoder(categorical_features=[0])
    onehotencoder_1 = OneHotEncoder(categorical_features=[1])
    onehotencoder_2 = OneHotEncoder(categorical_features=[2])
    X = onehotencoder_0.fit_transform(X).toarray()
    X = onehotencoder_1.fit_transform(X).toarray()
    X = onehotencoder_2.fit_transform(X).toarray()
     Encoding categorical data y
    from sklearn.preprocessing import LabelEncoder
    labelencoder_y = LabelEncoder()
    y = labelencoder_y.fit_transform(y)
    max(y)

Splitting the dataset into the Training set and Test set

        #from sklearn.cross_validation import train_test_split
          from sklearn.model_selection import train_test_split
    X_train, X_test, y_train, y_test = train_test_split(X, y, 
                                                        test_size = 0.2, 
                                                        random_state = 1)
    """sc_y = StandardScaler()
    y_train = sc_y.fit_transform(y_train)"""

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

Fitting Random Forest Classification to the Training set

        from sklearn.ensemble import RandomForestClassifier
    classifier = RandomForestClassifier(n_estimators = 500, 
                                        criterion = 'entropy', 
                                        random_state = 0,
                                        oob_score = True)
    classifier.fit(X_train, y_train)

    y_pred = classifier.predict(X_test)

Making the Confusion Matrix

      from sklearn.metrics import confusion_matrix
    cm = confusion_matrix(y_test, y_pred)


    from sklearn.model_selection import cross_val_score
    accuracies = cross_val_score(estimator= classifier, 
                                 X = X_train,
                                 y = y_train,
                                 cv=10)

    accuracies_mean = accuracies.mean()
    accuracies_std = accuracies.std()

    print("Accuracy and STD of RF")
    print(accuracies_mean)
    print(accuracies_std)

Keras Model

    model = Sequential()
    model.add(Dense(12, input_dim=45, activation='relu'))
    model.add(Dense(8, activation='relu'))
    model.add(Dense(1, activation='sigmoid'))


    from keras import optimizers

    numpy.random.seed(7)
    import datetime, os
    logdir = os.path.join("logs", datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
    tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
    sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)

    model.compile(loss='mean_squared_error', optimizer=sgd, metrics=['accuracy'])

    sgd = optimizers.SGD(lr=0.01, clipnorm=1.)


              model.fit(X_train, y_train,
              batch_size=50000,
              epochs=10,
              verbose=1,
              validation_data=(X_test, y_test),
              callbacks=None)

    y_pred = model.predict(X_test)

    score = model.evaluate(X_test, y_test, verbose=1)

suggest me how i can improve accuracy of keras

Answer 1

You are in a classification (and not regression) setting, so you should not use MSE as your loss function in Keras (it is for regression problems); change your model compilation to

model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy'])

See What function defines accuracy in Keras when the loss is mean squared error (MSE)? for more details, albeit in an "inverse" setting (trying to use accuracy in a regression problem).

Your batch_size=50000 looks extremely high, but if you don't run into memory problems it could do.