Deep reinforcement one-shot learning for artificially intelligent classification in expert aided systems
یادگیری تقویتی عمیق یک شات برای طبقه بندی هوشمندانه مصنوعی در سیستم های خبره-2020
In recent years there has been a sharp rise in applications, in which significant events need to be classified but only a few training instances are available. These are known as cases of one-shot learning. To handle this challenging task, organizations often use human analysts to classify events under high uncertainty. Existing algorithms use a threshold-based mechanism to decide whether to classify an object automatically or send it to an analyst for deeper inspection. However, this approach leads to a significant waste of resources since it does not take the practical temporal constraints of system resources into account. By contrast, the focus in this paper is on rigorously optimizing the resource consumption in the system which applies to broad application domains, and is of a significant interest for academic research, industrial developments, as well as society and citizens benefit. The contribution of this paper is threefold. First, a novel Deep Reinforcement One-shot Learning (DeROL) framework is developed to address this challenge. The basic idea of the DeROL algorithm is to train a deep-Q network to obtain a policy which is oblivious to the unseen classes in the testing data. Then, in real-time, DeROL maps the current state of the one-shot learning process to operational actions based on the trained deep-Q network, to maximize the objective function. Second, the first open-source software for practical artificially intelligent one-shot classification systems with limited resources is developed for the benefit of researchers and developers in related fields. Third, an extensive experimental study is presented using the OMNIGLOT dataset for computer vision tasks, the UNSW-NB15 dataset for intrusion detection tasks, and the Cleveland Heart Disease Dataset for medical monitoring tasks that demonstrates the versatility and efficiency of the DeROL framework.
Keywords: Deep reinforcement learning | One-shot learning | Network optimization | Online classification
Probabilistic active learning: An online framework for structural health monitoring
یادگیری فعال احتمالی: یک چارچوب آنلاین برای نظارت بر سلامت ساختاری-2019
A novel, probabilistic framework for the classification, investigation and labelling of data is suggested as an online strategy for Structural Health Monitoring (SHM). A critical issue for data-based SHM is a lack of descriptive labels (for measured data), which correspond to the condition of the monitored system. For many applications, these labels are costly and/or impractical to obtain, and as a result, conventional supervised learning is not feasible. This fact forces a dependence on outlier analysis, or one-class classifiers, in practical applications, as a means of damage detection. The model suggested in this work, however, allows for the definition of a multi-class classifier, to aid both damage detection and identification, while using a limited number of the most informative labelled data. The algorithm is applied to three datasets in the online setting; the Z24 bridge data, a machining (acoustic emission) dataset, and measurements from ground vibration aircraft tests. In the experiments, active learning is shown to improve the online classification performance for damage detection and classification.
Keywords: Damage detection | Pattern recognition | Semi-supervised learning |Structural health monitoring
Online Transfer Learning
آموزش انتقال آنلاین-2014
In this paper, we propose a novel machine learning framework called “Online Transfer Learning” (OTL), which aims to attack an online learning task on a target domain by transferring knowledge from some source domain. We do not assume data in the target domain follows the same distribution as that in the source domain, and the motivation of our work is to enhance a supervised online learning task on a target domain by exploiting the existing knowledge that had been learnt from training data in source domains. OTL is in general very challenging since data in both source and target domains not only can be different in their class distributions, but also can be diverse in their feature representations. As a first attempt to this new research problem, we investigate two different settings of OTL: (i) OTL on homogeneous domains of common feature space, and (ii) OTL across heterogeneous domains of different feature spaces. For each setting, we propose effective OTL algorithms to solve online classification tasks, and show some theoretical bounds of the algorithms. In addition, we also apply the OTL technique to attack the challenging online learning tasks with concept-drifting data streams. Finally, we conduct extensive empirical studies on a comprehensive testbed, in which encouraging results validate the efficacy of our techniques. Keywords: Transfer learning Online learning Knowledge transfer