Deep Learning
Pembelajaran Mendalam
Machine learning with many-layered networks that learn their own features.
Deep learning is machine learning where feature extraction is learned rather than hand-designed. An old-school vision pipeline had a human decide what a "corner detector" means; a deep network learns that from raw pixels. The word "deep" refers to the number of stacked layers. The practical shift is that deep learning removed the human feature-engineering step, which is why it took over image and speech recognition, and later language.
Related terms
Neural Network
A stack of weighted layers that transforms input into output by adjusting numbers.
Machine Learning
Programs that improve from examples instead of hand-written rules.
Training
The expensive process that sets a model's parameters by exposing it to data.
LLM
A model trained on a huge amount of text to predict the next token. The engine behind most AI products.
Want this working inside your team?
It starts with one conversation about your workflow.