Neural Network

A neural network is a computational model loosely inspired by the brain, built from layers of simple units called neurons. Each connection has a weight; training adjusts those weights so the network's outputs match known answers.

Why it matters

Neural networks are the core technology behind deep learning, image recognition, speech-to-text, and language models. Their flexibility lets one design learn many tasks when given the right data.

Example

A tiny network has an input layer, one hidden layer, and an output layer. Each neuron computes a weighted sum of its inputs and applies an activation function:

output = activation(w1*x1 + w2*x2 + b)

Training uses backpropagation to compute how much each weight contributed to the error, then gradient descent nudges the weights to reduce it.

Common mistakes

• Assuming the structure mirrors a real brain. The resemblance is only loose.
• Training without a held-out validation set, so overfitting goes unnoticed.
• Using a network when the dataset is tiny and a simpler model would generalize better.

Related

• Deep learning
• Transformer
• Training data
• Inference

यह पेज सामान्य जानकारी है, जिसे हमारी संपादकीय टीम ने लिखा है और दस्तावेज़ीकरण बदलने पर अपडेट किया जाता है। सर्वर और प्रदाता अलग-अलग होते हैं, इसलिए बदलाव पहले सुरक्षित तरीके से जाँचें। देखें: संपादकीय नीति और अस्वीकरण.