Multiclass classification
Multiclass classification is a supervised prediction task that assigns each input to exactly one of more than two possible classes.
Deep Learning with R, Third Edition
A multiclass classification model is a predictive model that assigns inputs to one of more than two classes and produces scores or probabilities for those classes.
- How it is used
- Classifies vector inputs into one of more than two mutually exclusive categories, illustrated by newswire topics.
- How deep it goes
- Gives a worked task and practical output-layer and loss choices, without deriving the mathematics of softmax or cross-entropy.
- Examples
- Uses Reuters newswires assigned to 46 mutually exclusive topics.
- What you can do after
- Build it from scratch by matching a single-label classifier’s softmax units and cross-entropy loss to its classes and target encoding.
Read how Deep Learning with R, Third Edition explains multiclass classification →
Ensemble Methods for Machine Learning
Multiclass classification is a supervised prediction task whose target has more than two categorical classes.
- How it is used
- Frames supervised prediction problems whose labels belong to more than two categorical classes.
- How deep it goes
- Defines the task and demonstrates library-based ensemble use, while deferring general multiclass algorithms and detailed probability mechanics.
- Examples
- Uses Iris class prediction, LETOR relevance ranking, and per-class probabilities from ensemble classifiers.
- What you can do after
- Apply it via scikit-learn’s AdaBoostClassifier to train, predict, and measure error on multiclass data.
Read how Ensemble Methods for Machine Learning explains multiclass classification →
Related concepts
- classifierkind of · A classifier is a predictive computational model that assigns inputs to one or more discrete classes or categories.
- random forestused by · A random forest is an ensemble model that combines predictions from multiple decision trees built with randomized data samples, feature selections, or both.
- cross entropy lossused by · Cross-entropy loss measures the expected negative log probability that a predicted distribution assigns to outcomes drawn from a target distribution.
- multilabel classificationincludes · Multilabel classification is a classification task in which each input may be assigned zero or more labels simultaneously.
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.