Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization, and there is scarce work that looks to use these explanations as feedback to improve model performance. In this work, model explanations are fed back to the feed-forward training to help the model generalize better. To this extent, a custom weighted loss where the weights are generated by considering the Euclidean distances between true LIME (Local Interpretable Model-Agnostic Explanations) explanations and model-predicted LIME explanations is proposed. Also, in practical training scenarios, developing a solution that can help the model learn sequentially without losing information on previous data distribution is imperative due to the unavailability of all the training data at once. Thus, the framework incorporates the custom weighted loss with Elastic Weight Consolidation (EWC) to maintain performance in sequential testing sets. The proposed custom training procedure results in a consistent enhancement of accuracy ranging from 0.5% to 1.5% throughout all phases of the incremental learning setup compared to traditional loss-based training methods for the keyword spotting task using the Google Speech Commands dataset.

翻译：神经网络预测的可解释性对于理解特征重要性和获得对神经网络性能的可解释性至关重要。然而，神经网络结果的解释大多局限于可视化，利用这些解释作为反馈来改善模型性能的工作很少。在本文中，模型解释被反馈到前馈训练中，以帮助模型更好地泛化。为此，提出了一种自定义加权损失函数，其中权重通过考虑真实LIME（局部可解释模型无关解释）解释与模型预测的LIME解释之间的欧几里得距离生成。此外，在实际训练场景中，由于所有训练数据无法一次性获得，开发一种能够帮助模型在不丢失先前数据分布信息的情况下顺序学习的解决方案至关重要。因此，该框架将自定义加权损失与弹性权重巩固（EWC）相结合，以在顺序测试集中保持性能。对于使用Google Speech Commands数据集的关键词识别任务，与传统基于损失的训练方法相比，所提出的自定义训练过程在增量学习设置的所有阶段中，准确率持续提升0.5%至1.5%。