Convolution neural network
Defination: A convolutional neural network (CNN) is a type of
artificial neural network used primarily for image recognition
and processing, due to its ability to recognize patterns in
images
• CNNs are a subset of machine learning.
• A convolutional neural network (CNN) is a type of deep
learning algorithm that's used to analyse visual features
from data, particularly images.
• CNNs uses principles from linear algebra, such as matrix
multiplication, to identify patterns in images.
• CNNs need millions of labeled data points for training.
CNN (Convolutional Neural Network) architecture
CNN (Convolutional Neural Network) architecture
1. Input Layer: The input layer consists of image data,
represented as a 2D or 3D tensor .
2.Convolutional Layer: These layers apply convolutional
operations to input images, using filters (also known as
kernels) to detect features such as edges, textures, and
more complex patterns.
o Convolutional operations help preserve the spatial
relationships between pixels.
3. Pooling Layers: Pooling layers downsample the spatial
dimensions of the input, reducing the computational
complexity and the number of parameters in the network.
Max pooling is a common pooling operation, selecting the
maximum value from a group of neighboring pixels.
4.Fully Connected Layers: These layers are responsible for
making predictions based on the high-level features learned
by the previous layers. They connect every neuron in one
layer to every neuron in the next layer.
Steps:
CNNs are trained using a large dataset of labeled images,
where the network learns to recognize patterns and features
that are associated with specific objects or classes.
Proven to be highly effective in image-related tasks, achieving
state-of-the-art performance in various computer vision
applications.
Their ability to automatically learn hierarchical
representations of features makes them well-suited for tasks
where the spatial relationships and patterns in the data are
crucial for accurate predictions.
CNNs are widely used in areas such as image classification,
object detection, facial recognition, and medical image
analysis.
The convolutional layers are the key component of a CNN,
where filters are applied to the input image to extract
features such as edges, textures, and shapes.
The output of the convolutional layers is then passed through
pooling layers, which are used to down-sample the feature
maps, reducing the spatial dimensions while retaining the
most important information.
The output of the pooling layers is then passed through one
or more fully connected layers, which are used to make a
prediction or classify the image.
What is Pooling in Deep Learning?
Pooling is nothing other than down sampling of an image.
Role of pooling layer is to reduce the resolution of the feature
map but retaining features of the map required for
classification through translational and rotational invariants.
In addition to spatial invariance robustness, pooling will
reduce the computation cost by a great deal.
• Backpropagation is used for training of pooling
operation
• It again helps the processor to process things faster
Max pooling where we take largest of the pixel values of a
segment.
It captures the most prominent feature (e.g., the strongest
activation) in the region.
Advantages
Noise reduction:
Dimensionality reduction:
Avg pooling where we take largest of the pixel values of a
segment.
Averages the values in a region, instead of taking the
maximum, which leads to smoother outputs.
Global Average Pooling: Outputs the maximum value from
the entire feature map.
o Reduces the number of parameters significantly,
lowering the risk of overfitting.
o Simplifies the model architecture.
