Layer

How it is used

Networks have an input layer, hidden layers and an output layer. Engineers add, remove, freeze or unfreeze layers, and the 'deep' in deep learning refers to having many of them. Common types include dense, convolutional and attention layers.

Example sentences

1. We froze the first ten layers and trained only the top two.

2. Adding another hidden layer didn't help; the model just overfit faster.

Common collocations

• hidden layer
• output layer
• freeze layers
• add a layer
• dense layer

Related terms

• neural networkA model made of many connected units arranged in layers, loosely inspired by the brain. Each connection has a weight that is adjusted during training.
• deep learningThe part of machine learning that uses neural networks with many layers. It powers modern speech recognition, image recognition and large language models.
• activation functionA simple mathematical function applied to the output of each unit in a neural network. It adds non-linearity, which lets the network learn complex patterns.
• weightsThe learned numbers on the connections of a neural network, which decide how strongly each input affects the next layer. Together they hold what the model has learned.

This word in other fields

The same English word can have a different meaning in another field:

• layer · Artificial Intelligence & Machine Learning
• layer · Graphic Design

More terms: Machine Learning and Data Processing

• artificial intelligence
• machine learning
• model
• dataset
• training data
• label
• train
• supervised learning
• loss function
• overfitting
• test set
• accuracy