What is Neural Network?
Also known as: ANN
A neural network, or artificial neural network (ANN), is a computational model inspired by the human brain that learns to recognize patterns in data by passing information through layers of interconnected artificial neurons.
It consists of an input layer that receives data, one or more hidden layers that process it, and an output layer that produces results. Each connection between neurons has a weight that is adjusted during training.
The network learns by using algorithms like backpropagation to minimize errors between its predictions and the actual targets, often with activation functions that introduce non-linearity so it can model complex relationships.
Modern neural networks with many hidden layers are called deep neural networks and form the foundation of deep learning.
Example
A neural network trained on thousands of labeled photos can learn to classify new images as containing a cat or a dog by detecting edges, textures, and shapes across its layers.
Why it matters
Neural networks power most state-of-the-art AI systems today, enabling breakthroughs in image recognition, natural language processing, recommendation systems, and scientific discovery.
Frequently asked questions
It adjusts the weights of connections between neurons using training data and an optimization process like gradient descent to reduce prediction errors.
Related terms
Deep Learning is a subset of machine learning that uses multi-layered artificial neural networks to automatically learn complex patterns from large datasets.
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.
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.
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.
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.