Scribd
Upload
53 views12 pages

Convolutional Neural Network SPS, Summer 2022

Convolutional Neural Networks (CNNs) are specialized artificial neural networks designed for analyzing visual imagery, offering advantages over traditional artificial neural networks (ANNs) through layers that detect features and reduce input size. Key operations in CNNs include convolution and pooling, which help identify important patterns in images. CNNs are widely used in applications such as face detection, tumor identification, and image segmentation due to their high accuracy.

Uploaded by

rabby01601565625
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
53 views12 pages

Convolutional Neural Network SPS, Summer 2022

Convolutional Neural Networks (CNNs) are specialized artificial neural networks designed for analyzing visual imagery, offering advantages over traditional artificial neural networks (ANNs) through layers that detect features and reduce input size. Key operations in CNNs include convolution and pooling, which help identify important patterns in images. CNNs are widely used in applications such as face detection, tumor identification, and image segmentation due to their high accuracy.

Uploaded by

rabby01601565625
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

Convolutional Neural

CNN Network
SPS, Summer 2022
INTRODUCTION

In deep learning,
a convolutional neural
network is a class of
artificial neural
network most commonly
applied to analyze
visual imagery.
INTUITION OF CNN
Experiment of David H. How we see the world
Hubel and Torsten N.
Wiesel’s
WHY CNN, NOT ANN?

 Increases
Computation
 Prone to Overfitting
WHAT EXTRA CNN PROVIDES
THAN ANN?
 Convolutional Layer
 Pooling Layer
 Finally a fully Connected Neural Network.

Convolutional Layer and Max Pooling layer finds the


interesting patterns (or features) which are basic
building blocks of understanding images. By finding
important features we reduce the size of Input. The
result of Convolution layers works as input to FCNN.
SO WHAT IS CONVOLUTION?
convolution is a mathematical operation on two functions
(f and g). In CNN A convolution operation maps an input
to an output using a filter and a sliding window.
CONVOLUTION
TERMS RELATED WITH
CONVOLUTION
 Strides (how much to go)
 Filters (Find features)
 Padding (adding extra
bits)
an (8 x 8) image and (3 x
3) filter, the output
resulting after convolution
operation would be of size [(n x n) image] * [(f x f) filter] —> [(n – f + 1) x
(6 x 6). (n – f + 1) image]
To get the same padding use
the last formula. In both p
means padding layer number.
TERMS RELATED WITH
CONVOLUTION
Filters are matrixes of n*n shape
Filters are learned by CNN with Backpropagation.

Horizontal Edge
Detection
WHAT ABOUT COLORED
IMAGES?
APPLICATIONS
Detection(Face, Tumor,
OCR)
Classification
Image Segmentation

In Any kind of visual


sector CNN is still the
best choice for great
accuracy. CNN applications
are limitless now a days.
RESOURCES
https://poloclub.github.io/cnn-explainer/
https://adamharley.com/nn_vis/cnn/3d.html
https://deeplizard.com/resource/pavq7noze2
Hands-On Machine Learning with Scikit-Learn and
TensorFlow (Chapter 14)
Deep Learning with Python (Chapter 5)

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy