In many industrial applications, datasets are often obtained in a sequence associated with a series of similar but different tasks. To model these datasets, a machine‐learning algorithm, which performed well on the previous task, may not have as strong a performance on the current task. When the architecture of the algorithm is trained to adapt to new tasks, often the whole architecture needs to be revised and the old knowledge of modeling can be forgotten. Efforts to make the algorithm work for all the relevant tasks can cost large computational resources and data storage. Continual learning, also called lifelong learning or continual lifelong learning, refers to the concept that these algorithms have the ability to continually learn without forgetting the information obtained from previous task. In this work, we provide a broad view of continual learning techniques and their industrial applications. Our focus will be on reviewing the current methodologies and existing applications, and identifying a gap between the current methodology and the modern industrial needs.This article is categorized under: Technologies > Artificial Intelligence Fundamental Concepts of Data and Knowledge > Knowledge Representation Application Areas > Business and Industry

中文翻译：

---

持续学习及其工业应用：选择性回顾


在许多工业应用中，数据集通常是按照与一系列相似但不同的任务相关的序列获得的。为了对这些数据集进行建模，在先前任务中表现良好的机器学习算法在当前任务中可能表现不佳。当算法的架构被训练以适应新任务时，通常需要修改整个架构，并且旧的建模知识可能会被遗忘。使算法适用于所有相关任务的努力可能会花费大量的计算资源和数据存储。持续学习，也称为终身学习或持续终身学习，是指这些算法具有持续学习而不忘记从先前任务中获得的信息的能力。在这项工作中，我们提供了持续学习技术及其工业应用的广阔视野。我们的重点将是审查当前的方法和现有的应用程序，并确定当前的方法和现代工业需求之间的差距。本文分类如下：技术％3E人工智能数据和知识的基本概念％3E知识表示应用领域> 商业和工业