CNN Architecture ?

1. Input Layer

   • Example: 28x28 grayscale image (1 channel)

2. Convolution Layer

   • Applies filters (kernels) to extract features like edges or textures

3. ReLU Activation

   • Introduces non-linearity to the model

4. Max Pooling Layer

   • Reduces spatial dimensions (e.g., 2x2 pooling)

5. Flatten Layer

   • Converts 2D feature maps into a 1D vector

6. Fully Connected Layer

   • Dense layer that learns complex patterns

7. Output Layer (Softmax)

   • Produces probabilities for classification tasks

CNN or Convolutional Neural Network is a type of deep learning algorithm, used for tasks like image classification, object-detection and many more. Breakdown of each layer in CNN

1. Input Layer- This layer receives the input data.
2. Convolutional Layer- This layer applies convolutional operations to extract features, detect patterns by using filters.
3. Activation Layer- It uses Activation function like ReLU to introduce non-linearity to the network, allowing it to learn more complex patterns.
4. Pooling Layer- This layer reduces spatial dimensions of the feature maps, decreases computational load and prevent overfitting. Common pooling technique used in this layer is Max pooling.
5. Flattening- Pooled feature maps are flattened in a single vector, preparing for the fully conntected layers.
6. Fully Connected Layer- This layer connects neuron to their upcoming neuron, allowing to learn complex relationships between extracted features.
7. Output Layer- This layer produces the output, such as classification label or regression Value.

Filters- Small matrices that slide over the input data like an image to detect specific features

Activation function- Means that it will decide whether the neuron's input to the network is important or not in the process of prediction using simpler mathematical operations

Spatial dimension- width and height of an image or a feature map