What is Convolutional Neural Network?
Also known as: CNN
A Convolutional Neural Network (CNN) is a specialized type of deep neural network designed to process grid-like data such as images by automatically learning spatial patterns and features.
CNNs use convolutional layers that apply small filters (kernels) across the input to detect local features like edges or textures, producing feature maps that highlight where those patterns appear.
Pooling layers then reduce the size of these feature maps while keeping the most important information, which lowers computation and helps the network become more robust to small shifts in the data.
After several convolution and pooling stages, fully connected layers combine the detected features to make final predictions such as classifying an image.
Example
When shown photos of animals, a CNN can learn to first detect edges and colors, then combine them into shapes like ears or fur, and finally recognize the whole animal as a cat or dog.
Why it matters
CNNs power most modern computer vision systems, enabling accurate image recognition in applications from medical diagnosis to self-driving cars while using far fewer parameters than traditional neural networks.
Frequently asked questions
A CNN uses shared filters and local connections instead of connecting every neuron to every other neuron, making it much more efficient for images and other spatial data.
Related terms
An activation function is a mathematical operation applied to the output of a neuron in a neural network that decides whether the neuron should 'fire' and pass on a signal.
An autoencoder is a neural network that learns to compress input data into a smaller representation and then reconstruct the original data from that compressed form.
Backpropagation is an algorithm for training neural networks by calculating how much each weight contributed to the prediction error and adjusting those weights accordingly. It uses the chain rule to efficiently compute gradients of the loss function.
In deep learning, a decoder is a neural network module that converts an encoded representation (like a context vector or latent features) into a final output such as text, images, or sequences.
Long Short-Term Memory (LSTM) is a type of recurrent neural network architecture designed to learn and retain information over long sequences of data.
A Recurrent Neural Network (RNN) is a type of neural network built to handle sequential data by passing information from one step to the next through a hidden state that acts like a memory.