Artificial Neural Network

An artificial neural network (ANN) is a computational model loosely inspired by biological brains. It consists of layers of interconnected processing units — called neurons or nodes — that transform input data through a series of mathematical operations to produce outputs.

Basic structure

Every neural network has at least three parts. The input layer receives data — pixel values of an image, words in a sentence, or numbers in a spreadsheet. One or more hidden layers transform this data through weighted connections and mathematical functions. The output layer produces the result — a classification, a prediction, or generated content.

Each connection between neurons has a weight — a number that determines how strongly one neuron's output influences the next. During training, these weights are adjusted to improve the network's performance.

How learning happens

Neural networks learn through a process called backpropagation. The network makes a prediction, compares it to the correct answer, and calculates the error. It then works backwards through the layers, adjusting weights to reduce the error. This process repeats across millions of training examples until the network's predictions become accurate.

Types of neural networks

• Feedforward networks: Data flows in one direction, from input to output. Used for basic classification and regression tasks.
• Convolutional neural networks (CNNs): Specialised for processing grid-like data such as images. They detect features like edges, shapes, and textures.
• Recurrent neural networks (RNNs): Designed for sequential data like text or time series. They maintain memory of previous inputs.
• Transformers: The architecture behind modern language models. They process all input tokens simultaneously using attention mechanisms.

From simple to deep

When a neural network has many hidden layers, it is called a "deep" neural network, and training it is called "deep learning." Depth allows networks to learn increasingly abstract representations — early layers detect simple patterns while deeper layers combine them into complex concepts.