Pretraining

Q: How deeply does Inside Deep Learning: Math, Algorithms, Models cover pretraining?

Explains model surgery, weight initialization, feature intuition, and warm or frozen training, but stops short of formal guarantees.

As explained in Inside Deep Learning: Math, Algorithms, Models

A strategy of training a model on a source dataset before adapting it to a downstream task.

Pretraining initializes a model with weights learned on a source dataset before adapting it to a downstream task. In image classification, pretrained convolutional filters provide a stronger starting point than random weights, while a replacement output layer is learned for the new labels. section 13.2.1

A practical pretraining workflow is:

Load a model trained on a large source dataset such as ImageNet. section 13.2.1
Replace the final fully connected layer so its output matches the downstream classes; the new layer starts with random weights. section 13.2.1
Train the adapted model with warm or frozen pretrained weights, depending on the available target data. section 13.2.3 section 13.6

Adapting ResNet-18

Load a pretrained ResNet-18, then replace its output layer with a two-class linear layer for cat-versus-dog classification. Earlier convolutional filters retain features such as edges and color changes, while training adapts the network to the target data. section 13.2.1

How Inside Deep Learning: Math, Algorithms, Models covers it

Cover of Inside Deep Learning: Math, Algorithms, Models

liveBook manning.com

Read Inside Deep Learning: Math, Algorithms, Models on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Deep Learning with R, Third EditionUnsupervised pretraining is training a model on input data without manually supplied labels before adapting it to downstream tasks.
liveBook manning.com

Deep Learning with Python, Third EditionThe initial large-scale training phase used to learn broad language representations before task-specific fine-tuning.
liveBook manning.com

Build a Large Language Model (From Scratch)The initial training phase in which a language model learns general patterns from a large text corpus before task-specific adaptation.
liveBook manning.com

Time Series Forecasting Using Foundation ModelsPretraining is initial training of a model on a large dataset to learn general patterns and relationships before applying it to specific tasks.
liveBook manning.com

Build a Reasoning Model (From Scratch)The initial training stage in which a language model learns general statistical structure from large amounts of data before task-specific adaptation.
liveBook manning.com

The Art of AI Product DevelopmentPretraining is the initial training of a model on broad data before adapting it to specific tasks or domains.
liveBook manning.com

How Large Language Models WorkPretraining is the initial training of a model on broad data before adapting it to particular tasks or applications.
liveBook manning.com

Introduction to Generative AI, Second EditionThe initial training phase in which a model learns general representations or predictive behavior from a large corpus before task-specific adaptation.
liveBook manning.com

LLMs in ProductionPretraining is the initial training of a model on a large, broad dataset before adapting it to a specific task or domain.
liveBook manning.com

Sutskever's ListPretraining is the initial training of a model on a broad dataset before task-specific adaptation or evaluation.
liveBook manning.com

Data Without LabelsPretraining is an initial model-training stage that learns general patterns or representations before adaptation to a specific task.
liveBook manning.com

Build a Website with ChatGPTPretraining is the initial training of a model on large amounts of data to learn general patterns before task-specific use.
liveBook manning.com

Reinforcement Learning from Human FeedbackPretraining is the initial large-scale optimization of a model on broad data, commonly through next-token prediction.

Compare how 14 books explain pretraining →

Related concepts

foundational modelproduces · 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.
pretrained modelproduces · A pretrained model is a machine-learning model whose parameters were learned through prior training before it is used or adapted for a subsequent task.
next-token predictionuses · Next-token prediction is the task or training objective of estimating the token that follows a sequence, given its preceding tokens and any conditioning information.
datasetuses · A dataset is an organized collection of related data items, records, or observations treated as a unit for storage, processing, analysis, or computation.
zero-shot learningused by · Zero-shot learning is a setting in which a model performs a task or predicts categories without task-specific examples during training, adaptation, or inference, relying on learned knowledge and available task information.
similarity searchused by · Similarity search is a retrieval technique that finds or ranks items by comparing their representations with a query according to a similarity or distance measure.

This explainer was generated by Manning's knowledge graph from the text of Inside Deep Learning: Math, Algorithms, Models. The section links point to the parts of the book it draws on.