Freeze
Freezing is the practice of keeping selected model parameters unchanged during training or adaptation, typically while allowing other parameters to be updated.
Deep Learning with R, Third Edition
A frozen parameter is a model parameter excluded from optimization so that its value remains unchanged during further training.
- How it is used
- Preserves pretrained image features while training a classifier and reduces trainable parameters during large language model fine-tuning.
- How deep it goes
- Defines freezing, demonstrates trainable-weight changes and recompilation, then explains its memory role in LoRA without detailing optimizer internals.
- Examples
- Shows an Xception backbone with zero trainable weights and a frozen projection kernel paired with rank-eight LoRA matrices.
- What you can do after
- Apply it via Keras or KerasHub to freeze pretrained weights, check trainability, and recompile before training.
Read how Deep Learning with R, Third Edition explains freeze →
Deep Learning with Python, Third Edition
To keep selected model parameters unchanged during training so they do not receive optimizer updates.
- How it is used
- Protects pretrained representations while a new classifier learns, then supports controlled adaptation during fine-tuning.
- How deep it goes
- Defines weight immutability, shows Keras configuration and recompilation, and gives staged and partial fine-tuning procedures.
- Examples
- Uses a frozen Xception convolutional base, dense classifier, augmented image dataset, trainable-weight counts, and staged fine-tuning.
- What you can do after
- Operate/configure Keras models by freezing bases, training replacement classifiers, recompiling, and selectively unfreezing layers.
Read how Deep Learning with Python, Third Edition explains freeze →
Related concepts
- transfer learningcontrasts with · Transfer learning is a machine-learning technique that reuses knowledge learned from one task, domain, or dataset to improve learning or performance on another.
- warm startcontrasts with · Warm start is a technique that initializes training or optimization from prior parameters, data, or a related solution instead of starting from scratch.
- expert networkconfigures · An expert network is a specialized neural subnetwork within a mixture-of-experts model that processes inputs selected or routed to it by a gating mechanism.
- foundational modelconfigures · A base or foundation model is a pretrained model that provides learned parameters or capabilities as a starting point for reuse or adaptation to downstream tasks.
- fine-tuninguses · Fine-tuning is adapting a pretrained machine-learning model by training it further on targeted data or objectives for a task, domain, or behavior.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.