论文标题
两国Q学习的基于增强学习的手写数字识别
Reinforcement Learning Based Handwritten Digit Recognition with Two-State Q-Learning
论文作者
论文摘要
我们提出了基于深度学习和强化学习的简单而有效的混合分类器。 Q学习与两个Q-state和四个动作一起使用。常规技术使用从卷积神经网络（CNN）中提取的特征图，并将其纳入QSTATES以及过去的历史。由于特征地图的尺寸很高，因此这些方法的数量非常大，因此导致了这些方法的困难。由于我们的方法仅使用两种Q - 阶段，它很简单，并且具有优化的参数数量要少得多，因此具有直接的奖励函数。同样，该方法使用未开发的动作进行图像处理，以相对于其他当代技术。三个数据集已被用于该方法的基准测试。这些是MNIST数字图像数据集，USPS数字图像数据集和MATLAB数字图像数据集。已提出的混合分类器的性能已与其他当代技术（如建立了公认的强化学习技术，Alexnet，CNN-NER-NEAR-NERKENT CLAINGE分类器和CNNSupport Vecter Machine Classifier）进行了比较。我们的方法在所有使用的三个数据集上的这些当代混合分类器都优于这些当代混合分类器。
We present a simple yet efficient Hybrid Classifier based on Deep Learning and Reinforcement Learning. Q-Learning is used with two Q-states and four actions. Conventional techniques use feature maps extracted from Convolutional Neural Networks (CNNs) and include them in the Qstates along with past history. This leads to difficulties with these approaches as the number of states is very large number due to high dimensions of the feature maps. Since our method uses only two Q-states it is simple and has much lesser number of parameters to optimize and also thus has a straightforward reward function. Also, the approach uses unexplored actions for image processing vis-a-vis other contemporary techniques. Three datasets have been used for benchmarking of the approach. These are the MNIST Digit Image Dataset, the USPS Digit Image Dataset and the MATLAB Digit Image Dataset. The performance of the proposed hybrid classifier has been compared with other contemporary techniques like a well-established Reinforcement Learning Technique, AlexNet, CNN-Nearest Neighbor Classifier and CNNSupport Vector Machine Classifier. Our approach outperforms these contemporary hybrid classifiers on all the three datasets used.
