Loading…
Glossary term
A model made of layers of connected units, loosely inspired by the brain, that learns by adjusting the strength of its connections.
A neural network is built from simple units, often called neurons, arranged in layers. Each unit takes numbers in, multiplies them by learned weights, adds them up and passes the result through an activation function.
Training adjusts the weights so the network's outputs get closer to the right answers across many examples.
Every line is a weight the network learns during training.
A tiny neural network in PyTorch
import torch.nn as nn
net = nn.Sequential(
nn.Linear(3, 5), nn.ReLU(), # input -> hidden
nn.Linear(5, 2), # hidden -> output
)Neural networks are the foundation of deep learning and of nearly every current frontier AI system.