Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss due to catastrophic forgetting, or invades data privacy by revisiting used exemplars. Inspired by linear learning formulations, we propose an analytic class-incremental learning (ACIL) with absolute memorization of past knowledge while avoiding breaching of data privacy (i.e., without storing historical data). The absolute memorization is demonstrated in the sense that class-incremental learning using ACIL given present data would give identical results to that from its joint-learning counterpart which consumes both present and historical samples. This equality is theoretically validated. Data privacy is ensured since no historical data are involved during the learning process. Empirical validations demonstrate ACIL's competitive accuracy performance with near-identical results for various incremental task settings (e.g., 5-50 phases). This also allows ACIL to outperform the state-of-the-art methods for large-phase scenarios (e.g., 25 and 50 phases).
translated by 谷歌翻译
我们考虑在非负轨道中包含的半格式集中的多项式优化问题(POP)(紧凑型集合上的每个POP都可以通过对Origin的简单翻译来以这种格式放置)。通过将每个变量平行,可以将这样的POP转换为等效的POP。使用偶数对称性和因子宽度的概念,我们根据Dickinson-Povh提出了基于P \'Olya的Potitivstellensatz的扩展,提出了半决赛弛豫的层次结构。作为其显着特征和关键特征,可以任意选择每个结果的半芬特弛豫的最大矩阵大小,此外,我们证明了新层次结构返回的值的序列收敛到原始POP的最佳值,以$ o的速率$ o。 (\ varepsilon^{ - c})$如果半gebraic集具有非空内饰。当应用于(i)多层神经网络的鲁棒性认证和(ii)计算积极的最大奇异值时,我们的方法基于p \'olya的Potitivstellensatz提供了更好的界限,并且比标准瞬间层次结构更快地运行了几百倍。
translated by 谷歌翻译
越来越多的人期望在对象属性具有高感知不确定性的越来越多的非结构化环境中操纵对象。这直接影响成功的对象操纵。在这项工作中,我们提出了一个基于增强的学习动作计划框架,用于对象操纵,该框架既利用了在现有的多感觉反馈,也可以使用学习的注意力引导的深层负担能力模型作为感知状态。可承受的模型是从多种感官方式中学到的,包括视觉和触摸(触觉和力/扭矩),旨在预测和指示具有相似外观的物体的多个负担能力(即抓地力和推动力)的可操作区域属性(例如,质量分布)。然后,对基于DQN的深钢筋学习算法进行培训,以选择成功对象操纵的最佳动作。为了验证提出的框架的性能,使用开放数据集和收集的数据集对我们的方法进行评估和基准测试。结果表明,所提出的方法和整体框架的表现优于现有方法,并实现更好的准确性和更高的效率。
translated by 谷歌翻译