Neural Network
Jaringan Syaraf Tiruan
A stack of weighted layers that transforms input into output by adjusting numbers.
A neural network is a large set of numbers (weights) arranged in layers. Input flows forward, each layer multiplies it by its weights, and the output of one layer becomes the input of the next. Training adjusts those numbers so the output gets closer to the desired answer. Nothing in the network resembles a rule a human wrote; the behaviour emerges from the numbers, which is why it can be hard to explain and easy to fool.
Related terms
Deep Learning
Machine learning with many-layered networks that learn their own features.
Parameters
The learned numbers inside a model. Their count is the model size.
Training
The expensive process that sets a model's parameters by exposing it to data.
Transformer
The neural network design behind nearly every modern language model.
Want this working inside your team?
It starts with one conversation about your workflow.