CNN(Convolutional Neural Networks)

 Introduction:

Convolutional Neural Networks (CNNs) are a type of deep learning algorithm that have revolutionized the field of computer vision. They are specifically designed to process image data and have been widely adopted in applications such as image classification, object detection, and image segmentation. In this blog, we will delve into the workings of a CNN and understand its key components.


The Key Components of a CNN

A CNN is made up of multiple layers including convolutional layers, activation layers, pooling layers, and fully connected layers. Let's take a closer look at each of these components:

Convolutional Layer:

The convolutional layer is the heart of a CNN and is responsible for performing the convolution operation on the input image. The convolution operation involves applying a set of filters to the input image to extract important features. These filters can be thought of as small matrices that are multiplied with small regions of the image to produce a new feature map. The formula for the convolution operation can be expressed as:

y = f * x

where f is the filter, x is the input image, and y is the output feature map. The size of the filter determines the size of the region of the image that is processed at a time.

There are different types of filters that can be used in a CNN, including edge detection filters, which detect edges in the image, and Gabor filters, which detect textures. The filters are learned by the network during training and can be adjusted to detect specific features in the image.

Activation Layer:

The activation layer is responsible for adding non-linearity to the network, allowing it to learn complex relationships between the features and the image classes. Non-linear functions used in activation layers include the ReLU (rectified linear unit) and sigmoid functions. The ReLU function is defined as:

f(x) = max(0,x)



where x is the input to the activation layer. The sigmoid function is defined as:

f(x) = \frac{1}{1 + e^{-x}}

where x is the input to the activation layer.

Pooling Layer:

The pooling layer is used to down sample the feature map from the activation layer, reducing its spatial dimensions and reducing the number of parameters in the network. This helps to reduce the computational cost of the network and also reduces overfitting, as the network is forced to learn more robust features. There are different types of pooling operations that can be used in a pooling layer, including max pooling and average pooling. 
Max pooling selects the maximum value in each region of the feature map.
while Average pooling takes the average value in each region.


Min pooling is another type of pooling operation that can be used in a pooling layer of a CNN. It works similarly to max pooling, but instead of selecting the maximum value in each region of the feature map, it selects the minimum value. The idea behind min pooling is to preserve the information about the darkest regions in the feature map, which can be useful for certain types of image processing tasks.

The min pooling operation can be expressed mathematically as:

y_{i,j} = min(x_{i:i+h-1,j:j+w-1})


Flattened Layer:

After the pooling layer, the next step in a Convolutional Neural Network (CNN) is to flatten the output of the pooling layer into a single vector. This process is known as flattening and is done to prepare the feature map for the fully connected layer.

The flattening operation simply takes the output of the pooling layer and unrolls it into a single, long vector. This vector is then passed as input to the fully connected layer. The reason for flattening the feature map is to allow the fully connected layer to have a single node for each feature, which can be trained to make a prediction based on the features.

The formula for flattening the output of the pooling layer can be expressed as:

x = [x_1, x_2, ..., x_n]

where x is the output of the pooling layer and x1, x2, ..., xn are the individual elements of the feature map. The flattened output is then passed as input to the fully connected layer for making predictions.

It's important to note that flattening is just one step in the overall process of a CNN, and its role is to prepare the output of the pooling layer for the fully connected layer. The fully connected layer is responsible for making the final prediction based on the features extracted by the CNN.



Fully Connected Layer:

The fully connected layer is used to make predictions based on the features extracted by the previous layers. It is responsible for combining the information from the feature map and making a final prediction. Common loss functions used to train a CNN include cross-entropy and mean squared error.



Example of CNNs in Image Classification: One of the most common applications of CNNs is in image classification, where the goal is to predict the class of an input image. For example, a CNN could be trained to recognize different breeds of dogs in images. During training, the network would be shown many images of different dog breeds and learn to extract features that are important for differentiating between the classes. When making a prediction on a new image, the CNN would use the learned features to determine the class



                ** The End **


Comments

Post a Comment

Popular posts from this blog

Ridge, Lasso And ElasticNet Regression .

Image
  OVERVIEW This blog is going to be very interested for the understanding point of view for ridge ,lasso and elastic net regression . Let first understand what is lasso and Ridge and  ElasticNet. Before moving to Ridge, Lasso and Elastic Net Regression we need an basic idea of Overfitting and Underfitting. Let have an brief idea about it. Overfitting and Underfitting    Overfitting  is a condition where bias is low but variance tends to get high and results in fitting too much in a model, whereas in  Underfitting , the variance is low but bias tends to get high and the model becomes too loose or simplified. Also, when we can’t examine anything from the  machine learning algorithm ,  we can say it is an underfitting condition, whereas, when data provides excessive information that we don’t even need and this data is acting as a burden, we say it is an overfitting problem. Graphical representation of Underfitting, Just Fitting, and Overfitting The p...
Read more

Performance Metrices for classification and Regression.

Image
  Performance Metrics in Machine Learning Evaluating the performance of a Machine learning model is one of the important steps while building an effective ML model.  To evaluate the performance or quality of the model, different metrics are used, and these metrics are known as performance metrics or evaluation metrics.  These performance metrics help us understand how well our model has performed for the given data. In this way, we can improve the model's performance by tuning the hyper-parameters. Each ML model aims to generalize well on unseen/new data, and performance metrics help determine how well the model generalizes on the new dataset. In machine learning, each task or problem is divided into  classification  and  Regression . Not all metrics can be used for all types of problems; hence, it is important to know and understand which metrics should be used. Different evaluation metrics are used for both Regression and Classification tasks. In this top...
Read more