Scribd Logo
Upload

Welcome to Scribd!

  • Deep Learning Section5 (2023)

    Uploaded by

    sama ghorab
    4 views17 pages
    1) Convolutional neural networks (CNNs) are a type of neural network that specializes in processing grid-like images through a series of convolutional and pooling layers. 2) CNNs typically contain three types of layers: convolutional layers that extract features, pooling layers that reduce dimensionality and retain important information, and fully connected layers that help map representations between input and output. 3) Key functions of CNNs include convolutional layers that apply filters to extract features, pooling layers that perform downsampling via operations like max pooling, and fully connected layers that allow full connectivity between neurons to classify images.

    Original Description:

    Original Title

    Deep Learning Section5(2023)

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    1) Convolutional neural networks (CNNs) are a type of neural network that specializes in processing grid-like images through a series of convolutional and pooling layers. 2) CNNs typically contain three types of layers: convolutional layers that extract features, pooling layers that reduce dimensionality and retain important information, and fully connected layers that help map representations between input and output. 3) Key functions of CNNs include convolutional layers that apply filters to extract features, pooling layers that perform downsampling via operations like max pooling, and fully connected layers that allow full connectivity between neurons to classify images.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    4 views17 pages

    Deep Learning Section5 (2023)

    Uploaded by

    sama ghorab
    1) Convolutional neural networks (CNNs) are a type of neural network that specializes in processing grid-like images through a series of convolutional and pooling layers. 2) CNNs typically contain three types of layers: convolutional layers that extract features, pooling layers that reduce dimensionality and retain important information, and fully connected layers that help map representations between input and output. 3) Key functions of CNNs include convolutional layers that apply filters to extract features, pooling layers that perform downsampling via operations like max pooling, and fully connected layers that allow full connectivity between neurons to classify images.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    of 17

    Deep Learning

    ImageDataGenerator Class
    Convolutional Neural Network (CNN)
    • A Convolutional Neural Network, also known as CNN or ConvNet, is a
    class of neural network that specializes in processing data such as
    images. It contains a series of pixels arranged in a grid like fashion
    that contains pixel values to denote how bright and what color that
    each pixel has.
    Convolutional Neural Network (CNN)
    Convolutional Neural Network (CNN)
    • CNN typically has three layers:
    1) Convolutional Layer.
    2) Pooling Layer.
    3) Fully connected or Dense Layers .
    Convolutional Neural Network (CNN)
    Convolutional Neural Network (CNN)
    • The primary purpose of convolutional layer is to extract the features
    of the input images.

    • The Output of convolutional layer can be calculated by:

    𝑛
    y=σ𝑖 𝑥 ∗𝑓
    Convolutional Neural Network (CNN)
    • If we have an input of size W x W x D and Dout number of kernels
    with a spatial size of F with stride S and amount of padding P, then
    the size of output volume can be determined by the following
    formula:

    𝑊 − 𝐹 + 2𝑃
    𝑊𝑜𝑢𝑡 = +1
    𝑆
    Convolutional Neural Network
    Convolutional Neural Network (CNN)
    Convolutional Neural Network (CNN)
    Convolutional Neural Network (CNN)
    • ReLU stands for rectified linear unit and it’s a type of activation
    functions.
    • F(x)=max(0,x).
    2 3 2 2 3 2
    0 2 1 0 2 1
    -2 1 0 0 1 0
    Input of ReLU Output of ReLu
    Convolutional Neural Network
    (Pooling Layer)
    • Pooling layers will reduce the number of parameters when the inputs
    are too large.
    • Polling also called down sampling which reduces the dimensionality
    of each map but retains important information.
    • There are three types of pooling layers namely, Max Pooling, Average
    Pooling, Sum pooling.
    Convolutional Neural Network
    (Pooling Layer)
    • The most popular process is max pooling, which reports the
    maximum output from the neighborhood.
    Convolutional Neural Network (Flatten Layer)
    • The feature matrix will be converted as vector.

    6
    6 8 8
    3 4 3
    4
    Input Output
    Convolutional Neural Network (Fully
    Connected Layer)
    • In Fully connected layer, neurons in this layer have full connectivity
    with all neurons in the preceding and succeeding layer as seen in
    regular FCNN. This is why it can be computed as usual by a matrix
    multiplication followed by a bias effect.

    • The FC layer helps to map the representation between the input and
    the output.
    Convolutional Neural Network (Fully
    Connected Layer)

    You might also like