What is a Neural Network?
Class 12 · Artificial Intelligence
6.1 What is a Neural Network?
A Neural Network is a machine learning model inspired by the structure and working of the human brain. It consists of interconnected nodes called neurons that process information and learn patterns from data.
Neural networks are a major component of Artificial Intelligence (AI) and Deep Learning. They can learn from examples, identify relationships in data and use the learned patterns to make predictions or decisions.
A neural network learns patterns from data by processing information through interconnected neurons arranged in different layers.
Biological Inspiration
The concept of a neural network is inspired by the human nervous system. In the human brain, biological neurons receive signals, process information and transmit signals to other neurons.
Artificial Neural Networks imitate this basic idea using mathematical models. Artificial neurons receive inputs, process them and produce outputs.
Artificial Neural Network
An Artificial Neural Network (ANN) is a computing system made up of interconnected artificial neurons. These neurons are arranged in layers and communicate with one another through connections.
| Term | Meaning |
|---|---|
| Neuron / Node | A basic processing unit of a neural network that receives inputs and produces an output. |
| Connection | A link between neurons through which information passes from one neuron to another. |
| Weight | A numerical value that represents the importance or strength of a connection. |
| Layer | A group of neurons arranged at the same level within the neural network. |
Basic Structure of a Neural Network
A basic neural network consists of an Input Layer, one or more Hidden Layers, and an Output Layer.
| Layer | Function |
|---|---|
| Input Layer | Receives the input data or features provided to the neural network. |
| Hidden Layer | Processes the input information and helps the network identify patterns and relationships. A neural network may contain one or more hidden layers. |
| Output Layer | Produces the final prediction, classification or other required output. |
How Does a Neural Network Learn?
A neural network learns by processing training data and adjusting the values of its weights and biases. During training, the network compares its predicted output with the expected output and adjusts its parameters to reduce the error.
This learning process is repeated over many examples until the neural network becomes better at making predictions.
Input → Process → Output
Input data enters the network, neurons process the information through hidden layers, and the output layer produces the final result.
Deep Neural Network
When an Artificial Neural Network contains two or more hidden layers, it is generally referred to as a Deep Neural Network (DNN).
Deep Neural Networks form the foundation of Deep Learning and are capable of learning complex patterns from large datasets.
Applications of Neural Networks
Neural networks are used in many real-world applications where computers need to identify patterns, classify information or make predictions.
- Image and face recognition
- Speech recognition
- Natural Language Processing
- Recommendation systems
- Medical diagnosis
- Fraud detection
- Weather and demand prediction
- Autonomous vehicles
Suppose a school wants to develop an AI system that predicts whether a student is likely to require additional academic support.
The system may use information such as attendance, assessment performance and previous academic records as input data.
A neural network can learn patterns from historical student data and produce an output indicating the predicted level of academic support required.
Competency-Based Question
A school develops an AI system that uses students' attendance, assessment scores and previous academic performance to predict whether a student may need additional academic support.
Identify how a neural network can help in this situation.
Click to View Answer
The attendance, assessment scores and previous academic performance can be provided as input features to the neural network. The network processes these inputs through its neurons and hidden layers, learns patterns from historical training data and produces a prediction about the student's possible need for additional academic support.
Common Beginner Mistakes
- Thinking that a neural network is the same as the human brain.
- Assuming that every neural network contains only one hidden layer.
- Confusing a neuron with an entire neural network.
- Forgetting that neural networks learn from training data.
- Confusing weights with input values.
- Assuming that a neural network always produces a numerical prediction; it can also perform classification and other tasks.
Quick Revision
- A neural network is a machine learning model inspired by the human brain.
- Artificial Neural Networks consist of interconnected neurons or nodes.
- Neurons are arranged into input, hidden and output layers.
- The input layer receives data.
- Hidden layers process information and identify patterns.
- The output layer produces the final result.
- Weights represent the importance of connections between neurons.
- Neural networks learn by adjusting weights and biases during training.
- A network with two or more hidden layers is generally called a Deep Neural Network.
Memory Trick
I → H → O
Remember:
- I → Input Layer
- H → Hidden Layer
- O → Output Layer
Input → Hidden → Output
Exam Tips
- Define a neural network as a machine learning model inspired by the human brain.
- Remember the three basic layers: Input, Hidden and Output.
- Clearly explain the function of each layer in descriptive questions.
- Remember that neurons are the basic processing units of a neural network.
- Remember that weights determine the strength or importance of connections.
- For questions on Deep Neural Networks, remember: two or more hidden layers.
- Use examples such as face recognition, speech recognition and prediction to support your answers.
Frequently Asked Questions (FAQs)
1. What is a neural network?
A neural network is a machine learning model inspired by the human brain that consists of interconnected neurons arranged in layers to process data and learn patterns.
2. What is an Artificial Neural Network (ANN)?
An Artificial Neural Network is a computing system made up of interconnected artificial neurons that process information and learn patterns from data.
3. What are the basic layers of a neural network?
The basic layers are the Input Layer, Hidden Layer and Output Layer.
4. What is the function of the input layer?
The input layer receives the input features or data that are provided to the neural network.
5. What is the function of the hidden layer?
Hidden layers process information and help the neural network identify patterns and relationships in the data.
6. What is the function of the output layer?
The output layer produces the final prediction, classification or required result.
7. What is a Deep Neural Network?
A Deep Neural Network is an Artificial Neural Network containing two or more hidden layers.
8. What are neurons in a neural network?
Neurons, also called nodes, are the basic processing units of a neural network. They receive inputs, process them and produce outputs.
Summary
- A neural network is a machine learning model inspired by the human brain.
- Artificial Neural Networks contain interconnected neurons arranged in layers.
- The three basic layers are the input, hidden and output layers.
- The input layer receives data, hidden layers process the information, and the output layer produces the final result.
- Weights determine the strength or importance of connections between neurons.
- Neural networks learn by adjusting weights and biases during the training process.
- Deep Neural Networks contain two or more hidden layers and form an important foundation of Deep Learning.
- Neural networks are widely used for recognition, prediction, classification and other AI applications.
Next Topic: Parts of a Neural Network