Scribd Logo
Upload

Welcome to Scribd!

  • 6 views

    Feed Forward

    Uploaded by

    Sur Esh
    The document details how to implement a feed forward neural network in TensorFlow Keras for digit classification on the MNIST dataset. It covers loading and preprocessing the data, creating a sequential model with multiple dense layers, compiling and training the model, and making predictions on test data.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Feed Forward

    Uploaded by

    Sur Esh
    6 views5 pages
    The document details how to implement a feed forward neural network in TensorFlow Keras for digit classification on the MNIST dataset. It covers loading and preprocessing the data, creating a sequential model with multiple dense layers, compiling and training the model, and making predictions on test data.

    Original Title

    feed forward

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document details how to implement a feed forward neural network in TensorFlow Keras for digit classification on the MNIST dataset. It covers loading and preprocessing the data, creating a sequential model with multiple dense layers, compiling and training the model, and making predictions on test data.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    6 views5 pages

    Feed Forward

    Uploaded by

    Sur Esh
    The document details how to implement a feed forward neural network in TensorFlow Keras for digit classification on the MNIST dataset. It covers loading and preprocessing the data, creating a sequential model with multiple dense layers, compiling and training the model, and making predictions on test data.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 5

    4 .

    IMPLEMENT A FEED FORWARD IN TENSOR FLOW KERAS

    Aim:

    To Write a python program to implement a perceptron in tensorflowkeras

    Envionment.

    Algorithm:

    1.Import the necessary libraries for working with TensorFlow and Keras.

    2.Load the MNIST dataset using the mnist.load_data() function. This gives you
    two tuples: (x_train, y_train) and (x_test, y_test) containing the training and testing
    data respectively.

    3.Create a Sequential model using Sequential(). This means that you're building a
    linear stack of layers.

    4.using the compile() method. Specify the optimizer (e.g., 'adam'), the loss function
    (e.g., 'categorical_crossentropy' for multi-class classification), and the evaluation
    metrics (e.g., 'accuracy').

    5.Train the model using the fit() method. Provide the training data (x_train and
    y_train), set the number of epochs (e.g., 5), and specify the batch size (e.g., 32) for
    each training iteration. You can also use the validation data (x_test and y_test) to
    monitor the model's performance during training.

    6.After training, you can use the trained model to make predictions on new data.

    7.To get the predicted class for a test example, use the argmax() function to find
    the index of the class with the highest predicted probability. Print the predicted
    class.
    8.You can experiment with different architectures, activation functions, optimizer
    settings, and hyperparameters to improve the model's performance

    Program:
    import tensorflow as tf

    from tensorflow.keras.models import Sequential

    from tensorflow.keras.layers import Dense, Flatten

    from tensorflow.keras.datasets import mnist

    from tensorflow.keras.utils import to_categorical

    # Load and preprocess the MNIST dataset

    (x_train, y_train), (x_test, y_test) = mnist.load_data()

    x_train, x_test = x_train / 255.0, x_test / 255.0

    y_train = to_categorical(y_train, num_classes=10)

    y_test = to_categorical(y_test, num_classes=10)

    # Create a feed-forward neural network

    model = Sequential([

    Flatten(input_shape=(28, 28)),

    Dense(128, activation='relu'),

    Dense(64, activation='relu'),

    Dense(10, activation='softmax')

    ])
    # Compile the model

    model.compile(optimizer='adam', loss='categorical_crossentropy',
    metrics=['accuracy'])

    # Train the model

    model.fit(x_train, y_train, epochs=5, batch_size=32, validation_data=(x_test,


    y_test))

    # Make predictions

    predictions = model.predict(x_test)

    # Print the predicted class for the first test example

    predicted_class = tf.argmax(predictions[0]).numpy()
    OUTPUT:
    print("Predicted class:", predicted_class)

    You might also like