How deeply does Deep Learning with R, Third Edition cover class probability distribution?

Explains vector structure, normalization, maximum selection, softmax, and categorical crossentropy without deriving the underlying mathematics.

Class probability distribution

As explained in Deep Learning with R, Third Edition

A class probability is a model's estimated probability that an input belongs to a particular class, represented here as a distribution across all classes.

A class probability distribution is the model’s probability estimate for every possible class. Its entries form a vector whose values sum to 1, with one entry per class. section 4.2.5 section 4.2.3

Reading predictions

For a 46-topic classifier, predict() returns one 46-entry vector for each input. The largest entry identifies the predicted topic. In the digit example, predictions[1, 8] is 0.9993394, so class 8 receives the highest score. section 4.2.5

A distribution communicates more than the single winning class:

Each position corresponds to a different output class. section 4.2.3
Softmax produces scores that sum to 1, allowing the entries to be read as probabilities. section 2.1 section 4.2.5
Categorical crossentropy compares the predicted distribution with the true label distribution during training. section 4.2.3

predictions <- model |> predict(x_test)

Inspect the R prediction call that generates class probability distributions for new samples. section 4.2.5

How Deep Learning with R, Third Edition covers it

Cover of Deep Learning with R, Third Edition

liveBook manning.com

Read Deep Learning with R, Third Edition on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Data Without LabelsA probability score is a numerical estimate between zero and one representing the predicted probability of a classification event.

Compare how 2 books explain class probability distribution →

Related concepts

predict_probaproduced by · predict_proba is a classifier method that returns estimated probabilities for each possible class for supplied input samples.
LogitBoostused by · LogitBoost is a boosting algorithm that constructs an ensemble by optimizing logistic loss, typically through probability-based classification updates.
softmaxproduced by · Softmax is a function that exponentiates a vector of scores and normalizes the results into nonnegative values that sum to one.
generationused by · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.
categoryproduces · A category is a distinct class or label used to group or classify items, observations, or outcomes by type or shared meaning.
probability distributionequivalent to · A probability distribution is a mathematical specification assigning probabilities to the possible values or outcomes of a random variable, with total probability one.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with R, Third Edition. The section links point to the parts of the book it draws on.