Convolution Neural Network(CNN)

What it Includes
● What is CNN
● Architecture
● Types of CNN
● Applications of CNN
● Characteristics
● Advantages & Disadvantages
● Demo
What is Convolution Neural Network(CNN)?
● CNNs are widely used in images recognition, images classification,
objects detection, recognition faces etc.
● CNN image classification takes an input image, process it & classify it
under certain categories.
● CNN is another type of neural network that can be used to enable
machine to visualize things & perform tasks.
● Image classification is the task of taking an input image & outputting
a class or a probability of classes that best describes the image,
Convolution Neural Network Contd.
● CNN is a specialized type of neural network model designed for
working with image data.
● We want the computer to be able to differentiate between all the
images its given:-
○ For that computer perform image classification by looking for low
level features such as edges, curves & then building up to more
abstract concept through a series of convolution layers.
Architecture of CNN
Types of layers in Convolutional Network
Convolutional neural networks are distinguished from other neural networks by their superior performance with image,
speech, or audio signal inputs. They have three main types of layers, which are:

● Convolutional layer
● Pooling layer
● Fully-connected (FC) layer
● Convolutional Layer: The convolutional layer is the core building block of a CNN, and it is where the majority of
computation occurs. It requires a few components, which are input data, a filter, and a feature map.

We also have a feature detector, also known as a kernel or a filter, which will move across the receptive fields of the
image, checking if the feature is present. This process is known as a convolution.

● Pooling Layer: Pooling layers, also known as downsampling, conducts dimensionality reduction, reducing the
number of parameters in the input.

Similar to the convolutional layer, the pooling operation sweeps a filter across the entire input, but the difference is
that this filter does not have any weights. Instead, the kernel applies an aggregation function to the values within the
receptive field, populating the output array.

● Fully-Connected Layer: The name of the fully-connected layer aptly describes itself. As mentioned earlier, the pixel
values of the input image are not directly connected to the output layer in partially connected layers. However, in the
fully-connected layer, each node in the output layer connects directly to a node in the previous layer.
Applications:
Computer vision is a field of artificial intelligence (AI) that enables computers and systems to derive meaningful information
from digital images, videos and other visual inputs, and based on those inputs, it can take action.

● Marketing

● Healthcare

● Retail

● Automotive
Characteristics of CNN
● The layers of a CNN have neurons arranged in 3 dimensions - width, height and
depth.
● Automatic detection of the important features without any human supervision.
● Each neuron inside a convolutional layer is connected to only a small region of the
layer before it, called a receptive field.
● Unlike the classical image recognition where we define the images ourselves, CNN
takes the image’s raw pixel data, trains the model, then extracts the features
automatically for better classification.
Advantages and Disadvantages of CNN
Advantages:
○ Very high accuracy in image recognition problems.
○ Automatically detects the important features without any human supervision.
○ Weight sharing

Disadvantages:
○ CNN do not encode the position and orientation of object.
○ Lack of ability to be spatially invariant to the input data.
○ Lots of training data is required
References
● https://www.javatpoint.com/keras-convolutional-neural-network
● https://www.upgrad.com/blog/basic-cnn-architecture/
THANK YOU