How deeply does Outlier Detection in Python cover transfer learning?

Explains foundation models, embeddings, fine-tuning, self-supervision, and efficiency benefits, but stops short of implementation code.

Transfer learning

As explained in Outlier Detection in Python

Transfer learning is a technique that adapts knowledge learned by a model on one task or dataset to another task or dataset.

Transfer learning adapts knowledge learned by a neural network for one task to another task, reducing the effort required to train the second model. section 16.5.3

A foundation model learns reusable features, often through a self-supervised pretext task. Fine-tuning then reuses its embeddings, retraining the final layer or adding another layer for the new task. section 16.5.3

Transfer learning can provide practical advantages:

Reuse features that are relevant to both the original and target problems. section 16.5.3
Reduce training time and cost by starting from embeddings close to the target representation. section 16.5.3
Create large self-supervised training sets using pretext targets such as predicting image rotations. section 16.5.3

From cats and dogs to dog types

A network trained to distinguish cats from dogs can provide embeddings for a second network that distinguishes different types of dogs. This transfer is more feasible for images than for tabular data, where tables are generally much less alike. section 16.5.3

How Outlier Detection in Python covers it

liveBook manning.com

Read Outlier Detection in Python on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Inside Deep Learning: Math, Algorithms, ModelsA training approach that adapts a pretrained model to a new task, usually by reusing learned weights and matching the original preprocessing expectations.
liveBook manning.com

LLMs in ProductionTransfer learning is a machine-learning technique that adapts knowledge learned from one task or dataset to another task or domain.
liveBook manning.com

Natural Language Processing in Action, Second EditionTransfer learning is reusing knowledge learned from one task or dataset to improve learning on another task or dataset.
liveBook manning.com

Generative AI in ActionTransfer learning adapts knowledge learned from one task or dataset to improve performance on another task.
liveBook manning.com

Knowledge Graphs and LLMs in ActionTransfer learning is a machine-learning technique that reuses patterns learned from one task or domain to improve performance on another task or domain.
liveBook manning.com

Time Series Forecasting Using Foundation ModelsTransfer learning is a technique that applies knowledge learned by a model on one dataset or task to a different dataset or task.
liveBook manning.com

Grokking Machine LearningTransfer learning is a technique that adapts a pretrained model to a new task or dataset by continuing its training, often by modifying only some parameters.
liveBook manning.com

Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIA technique that adapts knowledge learned from one task or dataset to a related task.
liveBook manning.com

Sutskever's ListTransfer learning is a technique that adapts knowledge learned from one task or dataset to another task or dataset.
liveBook manning.com

Domain-Specific Small Language ModelsThe process of taking a model trained on one task or domain and applying it to a related task or domain, often with further tuning.

Compare how 11 books explain transfer learning →

Related concepts

fine-tuningused by · Fine-tuning is adapting a pretrained machine-learning model by training it further on targeted data or objectives for a task, domain, or behavior.
pretrained modeluses · 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.
embeddinguses · A numerical vector representation of an item or input that encodes features or relationships useful for computational tasks.
generalizationuses · Generalization is the extension of a pattern, model, solution, or conclusion beyond the specific examples or cases from which it was derived.
unlabeled datauses · Unlabeled data consists of examples that lack target labels or task-specific annotations.
causal invarianceused by · Causal invariance is the stability of a causal relationship across changes in environments or data distributions.

This explainer was generated by Manning's knowledge graph from the text of Outlier Detection in Python. The section links point to the parts of the book it draws on.