Scribd Logo
Upload

Welcome to Scribd!

  • 2017 - Lecture 5 - Smaller Network - CNN - 2 (Ming Li) (10 Slides)

    Uploaded by

    rvasiliou
    3 views10 pages
    This document compares and contrasts convolutional neural networks (CNNs) and fully connected neural networks. CNNs reduce the number of parameters by using local connections and shared weights between layers. They also use max pooling to downsample images while preserving important information. The overall CNN architecture alternates between convolutional and max pooling layers to create progressively smaller representations, followed by fully connected layers for classification.

    Original Description:

    Lecture 5 - Smaller Network - CNN [Ming Li]

    Original Title

    2017 - Lecture 5 - Smaller Network - CNN - 2 [Ming Li][10 Slides]

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    This document compares and contrasts convolutional neural networks (CNNs) and fully connected neural networks. CNNs reduce the number of parameters by using local connections and shared weights between layers. They also use max pooling to downsample images while preserving important information. The overall CNN architecture alternates between convolutional and max pooling layers to create progressively smaller representations, followed by fully connected layers for classification.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    3 views10 pages

    2017 - Lecture 5 - Smaller Network - CNN - 2 (Ming Li) (10 Slides)

    Uploaded by

    rvasiliou
    This document compares and contrasts convolutional neural networks (CNNs) and fully connected neural networks. CNNs reduce the number of parameters by using local connections and shared weights between layers. They also use max pooling to downsample images while preserving important information. The overall CNN architecture alternates between convolutional and max pooling layers to create progressively smaller representations, followed by fully connected layers for classification.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    of 10

    Convolution v.s.

    Fully Connected

    1 0 0 0 0 1 1 -1 -1 -1 1 -1
    0 1 0 0 1 0 -1 1 -1 -1 1 -1
    0 0 1 1 0 0 -1 -1 1 -1 1 -1
    1 0 0 0 1 0
    0 1 0 0 1 0
    0 0 1 0 1 0
    convolution
    image

    x1
    1 0 0 0 0 1
    0 1 0 0 1 0 x2
    Fully- 0 0 1 1 0 0
    1 0 0 0 1 0
    connected
    …
    …

    …
    …
    0 1 0 0 1 0
    0 0 1 0 1 0
    x36
    1 -1 -1 Filter 1 1 1
    -1 1 -1 2 0
    -1 -1 1 3 0
    4 0 3
    :

    …
    1 0 0 0 0 1
    0 1 0 0 1 0 0
    0 0 1 1 0 0 8 1
    1 0 0 0 1 0 9 0
    0 1 0 0 1 0 10: 0

    …
    0 0 1 0 1 0
    13 0
    6 x 6 image
    14 0
    fewer parameters! 15 1 Only connect to
    16 1 9 inputs, not
    fully connected
    …
    1 -1 -1 1 1
    :2 0
    -1 1 -1 Filter 1
    :3 0
    -1 -1 1
    :4 0 3
    :

    …
    1 0 0 0 0 1
    0 1 0 0 1 0 7 0
    :8 1
    0 0 1 1 0 0
    :9 0 -1
    1 0 0 0 1 0
    10:: 0
    0 1 0 0 1 0

    …
    0 0 1 0 1 0
    13 0
    6 x 6 image
    :
    14 0
    Fewer parameters :15 1
    :
    16 1 Shared weights
    Even fewer parameters
    :
    …
    The whole CNN
    cat dog ……
    Convolution

    Max Pooling
    Can repeat
    Fully Connected many
    Feedforward network
    Convolution times

    Max Pooling

    Flattened
    Max Pooling
    1 -1 -1 -1 1 -1
    -1 1 -1 Filter 1 -1 1 -1 Filter 2
    -1 -1 1 -1 1 -1

    3 -1 -3 -1 -1 -1 -1 -1

    -3 1 0 -3 -1 -1 -2 1

    -3 -3 0 1 -1 -1 -2 1

    3 -2 -2 -1 -1 0 -4 3
    Why Pooling

     Subsampling pixels will not change the object


    bird
    bird

    Subsampling

    We can subsample the pixels to make image smaller


    fewer parameters to characterize the image
    A CNN compresses a fully connected
    network in two ways:
     Reducing number of connections
     Shared weights on the edges
     Max pooling further reduces the complexity
    Max Pooling

    New image
    1 0 0 0 0 1 but smaller
    0 1 0 0 1 0 Conv
    3 0
    0 0 1 1 0 0 -1 1
    1 0 0 0 1 0
    0 1 0 0 1 0 Max 30 13
    0 0 1 0 1 0 Pooling
    2 x 2 image
    6 x 6 image
    Each filter
    is a channel
    The whole CNN
    3 0
    -1 1 Convolution

    3 1
    0 3
    Max Pooling
    Can repeat
    A new image
    many
    Convolution times
    Smaller than the original
    image
    The number of channels Max Pooling

    is the number of filters


    The whole CNN
    cat dog ……
    Convolution

    Max Pooling

    Fully Connected A new image


    Feedforward network
    Convolution

    Max Pooling

    Flattened A new image

    You might also like