Semi-supervised learning, which aims to construct learners that automatically exploit the
large amount of unlabeled data in addition to the limited labeled data, has been widely …

Artificial neural networks (ANN) have been applied effectively in numerous fields for the aim
of prediction, knowledge discovery, classification, time series analysis, modeling, etc. ANN …

Semi-supervised learning aims at training accurate prediction models on labeled and
unlabeled data. Its realization strongly depends on selecting pseudo-labeled data. The …

We consider the weakly supervised binary classification problem where the labels are
randomly flipped with probability $1-\alpha $. Although there exist numerous algorithms for …

A central goal of unsupervised learning is to acquire representations from unlabeled data or
experience that can be used for more effective learning of downstream tasks from modest …

Semi-supervised algorithms aim to learn prediction functions from a small set of labeled
observations and a large set of unlabeled observations. Because this framework is relevant …

Most unsupervised learning performs clustering. A well-known exception is autoencoder
neural networks, which learn how to code the input data into a (typically) lower-dimensional …

Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled
data. Existing SSL typically requires all classes have labels. However, in many real-world …