Machine learning continues to grow in popularity due to its ability to learn increasingly complex tasks. However, for many supervised models, the shift in a data distribution or the appearance of a new event can result in a severe decrease in model performance. Retraining a model from scratch with updated data can be resource intensive or impossible depending on the constraints placed on an organization or system. Continual learning methods attempt to adapt models to new classes instead of retraining. However, many of these methods do not have a detection method for new classes or make assumptions about the distribution of classes. In this paper, we develop an attention based Gaussian Mixture, called GMAT, that learns interpretable representations of data with or without labels. We incorporate this method with existing Neural Architecture Search techniques to develop an algorithm for detection new events for an optimal number of representations through an iterative process of training a growing. We show that our method is capable learning new representations of data without labels or assumptions about the distributions of labels. We additionally develop a method that allows our model to utilize labels to more accurately develop representations. Lastly, we show that our method can avoid catastrophic forgetting by replaying samples from learned representations.
翻译:机器学习因其学习日益复杂的任务的能力而越来越受欢迎。 但是,对于许多受监督的模型来说,数据分配的转变或新事件的出现可能导致模型性能的大幅下降。根据对一个组织或系统的限制,从零开始用更新的数据重新训练一个模型可能是资源密集或不可能的。 持续学习的方法试图将模型改换到新的类别,而不是再培训。 但是,许多这些方法没有新类别探测方法,也没有对类别分布作出假设。 在本文中,我们开发了一个基于Gausian Mixture(称为GMAT)的注意方法,它可以用标签或不带标签的方式学习可解释的数据表达方式。 我们把这种方法与现有的神经结构搜索技术结合起来,通过一个不断增长的迭代培训过程,为探测新事件以最佳数量表示制定算法。 我们显示,我们的方法是能够学习新的数据表述方式,而没有标签或标签分布假设。 我们还开发一种方法,使我们的模型能够使用标签来更准确地发展表述。 最后,我们证明我们的方法可以避免通过重新展示样品而忘记灾难性的印象。