multiclass classification

The classificationclassification, n.: Sorting things into categories — spam or not spam, which animal is in a photo, which language a text is written in — by learning from examples that are already labeled. task in which each input belongs to exactly one of K > 2 mutually exclusive classes. Some models handle K classes natively: decision treesdecision tree, n.: A model that makes a prediction by asking a series of yes-or-no questions about the input, like a flowchart, with each answer leading to the next question until it reaches a final answer., k-nearest neighborsk-nearest neighbors, n.: Predicting something about a new example by finding the few most similar examples already known and going with their majority answer, or their average., naive Bayesnaive Bayes, n.: A simple, fast way of sorting items into categories using probabilities, which pretends that each clue is independent of the others. It is the classic technique behind early email spam filters., multinomial logistic regressionlogistic regression, n.: A simple, widely used method for yes-or-no predictions that outputs a probability — say, a 70% chance a customer cancels — by passing a weighted sum of inputs through an S-shaped curve. and neural networks, which usually end in a softmaxsoftmax, n.: A formula that turns a list of raw scores into probabilities — all positive and adding up to one — with the biggest share going to the highest score. layer trained with cross-entropycross-entropy, n.: A score of how surprised a model's predictions are by what actually happens; lower is better. Language models are trained mainly by driving this number down on real text. loss. Inherently binary methods such as support vector machinessupport vector machine, n.: A classic method that separates two groups of examples with the widest possible gap — like laying the broadest possible road between them. A mathematical shortcut lets it draw curved boundaries too. are extended by decomposition: one-vs-restone-vs-rest, n.: A way to handle many categories with a method that only gives yes-or-no answers: train one detector per category ('this one or not?') and pick the category whose detector is most confident. trains K classifiers; one-vs-one trains K(K−1)/2 pairwise classifiers that vote; and error-correcting output codes give each class a binary code word learned bit by bit. Evaluation uses per-class metrics averaged equally across classes (macro averaging) or pooled over all examples (micro averaging), together with the multiclass confusion matrixconfusion matrix, n.: A table that counts a model's right and wrong answers by type, showing for each true category how often each category was predicted, so you can see exactly which things it mixes up. and top-k accuracy.

With 1,000 ImageNet classes, we report both top-1 and top-5 accuracy for the multiclass model.