What Is a Neural Network?
See how a computer can learn to tell a dog from a zebra by studying examples and improving after mistakes.
Neural networks explained visually
Follow the dog-and-zebra example to see how pixels, layers, weights, and feedback produce a prediction.
A computer learns from examples
Imagine showing a computer hundreds of pictures. Some contain dogs. Others contain zebras. For every picture, you tell the computer the correct answer. At first, its guesses may be poor. With practice and feedback, the guesses improve.
A neural network is a computer model that learns patterns from examples. It contains many small processing units called artificial neurons. These units work together to turn input information, such as image pixels, into a useful result.
Small clues become a complete answer
The computer does not see a zebra in the same way you do. It begins with pixel values. Early parts of the network can react to simple clues such as bright and dark edges. Later parts combine those clues into curves, ears, faces, and stripes. Deeper layers can combine these features into the idea of a complete animal.
Weights control which clues matter
Connections between artificial neurons have values called weights. A weight controls how much importance the network gives to a signal. Stripes may become an important clue for a zebra. Floppy ears and golden fur may support a dog prediction. During training, the network adjusts many weights so its answers become more accurate.
Feedback produces learning
Suppose the network sees a zebra but predicts a dog. Training compares that prediction with the correct answer. The network measures its error, then adjusts its weights slightly. Repeating this process across many examples helps reduce future errors.
Everyday uses
Neural networks help phones recognize faces, email services identify spam, cameras detect road users, and speech systems recognize spoken words. The input changes from one task to another, but the basic idea remains similar: learn useful patterns from examples and use those patterns on new information.
Quick check
What does an image network receive first?
It receives numerical pixel values, not complete ideas such as “dog” or “zebra.”
What does a weight do?
It controls how strongly one signal influences another part of the network.
How does the network improve?
Training compares predictions with correct answers and adjusts the weights to reduce errors.
Lesson 1 transcript
Imagine you want to teach a computer the difference between a dog and a zebra. You show it many pictures and provide the correct answer each time. In the beginning, the computer may guess. After enough examples and corrections, its answers begin to improve.
The system doing this work can be a neural network. A neural network is a computer model that learns patterns from examples. It contains many small processing units called artificial neurons. These neurons pass numerical information to one another.
When the network receives a picture, it does not immediately see a dog or a zebra. It starts with pixels. Each pixel becomes a number that describes information such as brightness and color.
The first layer looks for very simple clues. Some neurons may react to edges. Other neurons may react to light and dark areas. The next layer combines those clues into larger shapes. It may notice curves, ears, or stripes. Deeper layers combine those features and begin to recognize the complete animal.
The connections between neurons contain values called weights. Think of each weight as an importance control. A strong weight tells the network to pay more attention to a signal. Zebra stripes may receive strong importance when the network tries to recognize a zebra.
Now suppose the network sees a zebra but predicts a dog. During training, we compare its prediction with the correct answer. The network measures how wrong it was and adjusts its weights slightly. Then it tries again. Repeating this process with many examples helps the network make better predictions.
Neural networks take some inspiration from biological neurons, but they are far simpler than a human brain. They are mathematical systems built to recognize patterns.
You already encounter neural networks in everyday life. They can help a phone recognize a face, detect spam in email, understand spoken words, or find cars and people in a street image.
The important idea is simple. A neural network receives numbers, builds useful patterns through layers, makes a prediction, and improves through feedback. In the next lesson, we will look inside one artificial neuron and explain inputs, weights, and bias.