Algorithm on English AI Terms Dictionary

Multiplicative weight update method

Sat, 18 Jul 2026 10:08:53 +0000

Definition

The multiplicative weight update method is a fundamental online learning algorithm used to make decisions in uncertain environments. It maintains a set of weights for different strategies or experts, updating them multiplicatively based on their past performance. Strategies that perform well have their weights increased, while poor performers see their weights decreased. This method is widely used in game theory, optimization, and machine learning for constructing efficient prediction algorithms with provable convergence guarantees.

Instance-based learning

Sat, 18 Jul 2026 10:02:49 +0000

Definition

Also known as memory-based learning, this technique does not build a generalized model during training. Instead, it stores the entire training dataset. When a prediction is needed, it finds the most similar instances (neighbors) in the stored data and uses their labels to determine the output. K-Nearest Neighbors (KNN) is the most common algorithm in this category.

Summary

A lazy learning approach where predictions are made by comparing new inputs to stored training instances.

Co-training

Sat, 18 Jul 2026 09:49:31 +0000

Definition

This method leverages multiple distinct feature sets (views) of the same data points. Initially, two classifiers are trained on small labeled datasets from each view. They then predict labels for unlabeled data, selecting high-confidence predictions to augment the training set of the other classifier. This iterative process expands the effective training data size, improving generalization when labeled data is scarce but abundant unlabeled data exists.

Summary

Co-training is a semi-supervised learning algorithm where two views of the data are used to train separate classifiers that iteratively label unlabeled data for each other.