Active learning or query learning is a specified case of semi-supervised machine learning that utilizes the learning algorithm that interactively examines the information source to label the new data inputs with desired outputs. Active machine learning identifies the best label to learn by labeling the data dynamically and incrementally during the training phase. The main significance of active learning is maximizing the performance gain of the model with the use of the best-annotated samples as possible. The implementation of active learning comprises three approaches, stream-based selective sampling approach, pool-based sampling approach, and membership query synthesis approach. Common application areas of active learning are natural language processing, image classification, text classification, and medical imaging.
Active learning is an ongoing research field while integrated with deep learning models to build more accurate decision-making models. Deep learning models used in active learning are convolutional neural networks, long short-term memory, and adversarial networks. Recent developments of active learning are multi-label active learning, hybrid active learning, online machine learning, combining active learning and federated learning, and fair active learning.
• Active learning (AL) is a unique semiautomated machine learning approach attempts to maximize the performance gain of the model by marking the fewest samples.
• Active Learning selects the samples based on the query strategy with the highest value to construct the training set and With a large number of large-scale data sets with annotations, Deep AL-related research has ushered in large development opportunities.
• Although, Active learning faces some difficulties in applying its query strategy directly to Deep learning due to model uncertainty in deep learning and insufficient data for labeled samples.
• AL has significant potential to effectively reduce labeling costs through the ability to obtain labeled data for free to avoid human intervention and greatly improve the recognition accuracy when less labeled data is used.