How deeply does AI-Powered Search cover pooling?

Explains token-value aggregation and resulting dimensions, then demonstrates normalization and pairwise scoring without detailing pooling internals.

Pooling

As explained in AI-Powered Search

Pooling is the aggregation of multiple representation values into a single lower-level or fixed-size representation.

Pooling combines multiple representation values into one lower-level or fixed-size representation. In semantic search, SBERT pools a sentence’s BERT token embeddings into a single vector. section 13.4.3

Mean-token pooling averages the numeric values across a sentence’s token embeddings, producing one 768-dimensional embedding. This fixed-size vector can then support sentence-similarity comparisons. section 13.4.3

Comparing pooled sentence representations

Encode four phrases with a pretrained SentenceTransformer, normalize their embeddings, and calculate pairwise dot products. “It’s raining hard” and “it is wet outside” receive the highest shown similarity score, 0.669060, while unrelated phrases score lower.

How AI-Powered Search covers it

liveBook manning.com

Read AI-Powered Search on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Inside Deep Learning: Math, Algorithms, ModelsA neural-network operation that downsamples local neighborhoods by aggregating their values.
liveBook manning.com

Natural Language Processing in Action, Second EditionA pooling layer is a neural-network layer that aggregates neighboring activations to reduce their representation while retaining salient information.
liveBook manning.com

Math and Architectures of Deep LearningA downsampling operation on feature maps that reduces spatial resolution, often by local averaging or max selection.
liveBook manning.com

Build a Text-to-Image Generator (from Scratch)A pooling layer aggregates values within local spatial windows to produce a reduced or transformed feature representation.
liveBook manning.com

Evolutionary Deep Learning: Genetic algorithms and neural networksPooling is a neural-network operation that aggregates values within local regions to reduce spatial or feature-map dimensions.
liveBook manning.com

Graph Neural Networks in ActionA graph operation that reduces a collection of representations to a smaller representation, often for graph-level prediction.
liveBook manning.com

Deep Learning with PyTorch, Second EditionA downsampling technique that reduces spatial resolution by aggregating local regions of a feature map.

Compare how 8 books explain pooling →

Related concepts

convolutional neural networkused by · A convolutional neural network is a neural-network architecture that applies learned convolutional operations to extract patterns from structured data.
max poolingincludes · Max pooling is an aggregation operation that replaces each local or grouped region with its maximum value, often to downsample a representation.
downsamplingequivalent to · Downsampling is the reduction of data quantity, spatial resolution, temporal resolution, or sampling rate by retaining, selecting, or aggregating fewer representative values or observations.
upsamplingalternative to · Upsampling is a process that increases the number, density, or spatial or temporal resolution of samples or values in a dataset or representation by adding, duplicating, or estimating them.
gradientuses · A gradient is the vector of partial derivatives of a scalar function with respect to its variables, indicating its local rate and direction of change.

This explainer was generated by Manning's knowledge graph from the text of AI-Powered Search. The section links point to the parts of the book it draws on.