Knowledge extraction and retention based continual learning by using convolutional autoencoder-based learning classifier system
Knowledge extraction and retention based continual learning by using convolutional autoencoder-based learning classifier system
复制标题
DOI：
10.1016/j.ins.2022.01.043
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Muhammad Irfan;Jiangbin Zheng;Muhammad Iqbal;Zafar Masood;M. H. Arif
中科院分区：
文献类型：
--
作者：
Muhammad Irfan;Jiangbin Zheng;Muhammad Iqbal;Zafar Masood;M. H. Arif
一个理想的基于人工智能的自治系统，与动态环境交互作用，需要像人类一样不断学习。人类把学到的知识保留下来，积累起来，并用来解决相关问题。目前，大多数基于人工智能的系统缺乏这种能力，工作在孤立的学习范式中。在本文中，我们提出了一种新的持续学习模型来解决现实世界中具有挑战性的图像分类问题。该模型能够利用先前学习到的知识进行连续学习。它既可以处理多任务场景，也可以处理单个增量任务场景，而不是只覆盖多任务场景的各种现有模型。在该模型中，提出了一种深度卷积自动编码器来提取图像的特征。此外，提出了一种学习分类器系统，该系统具有有效的知识编码方案，用于将真实世界的图像映射到基于编码片段的紧凑知识表示。在三个基准图像数据集上进行了实验，以验证模型的有效性：(I)CORe50，(Ii)iCubWorld28，(Iii)STL-10。实验结果表明，在两种连续学习场景下，该模型的性能都优于基线方法和各种最新方法。
An ideal artificial intelligence-based autonomous system, interacting with a dynamic environment, is required to learn continuously as human do. Human beings retain the learned knowledge, accumulate, and utilize it to solve related problems. Currently, most artificial intelligence-based systems lack this capability and work in an isolated learning paradigm. In this paper, we present a novel continual learning model to solve the challenging problem of real-world images classification. The proposed model is capable of learning continuously by utilizing the previously learned knowledge. It can handle both multi-task and single incremental task scenarios as opposed to various existing models that cover only the multi-task scenarios. In the proposed model, a deep convolutional autoencoder is presented to extract features from images. In addition, a learning classifier system with an effective knowledge encoding scheme is proposed for mapping real-world images to code fragment-based compact knowledge representation. Experiments are conducted on three benchmark image datasets to validate the model: (i) CORe50, (ii) iCubWorld28, and (iii) STL-10. Experiments results demonstrate that the proposed model outperforms the baseline method as well as various state-of-the-art methods for both continual learning scenarios.