arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01298cs.CVcs.LGeess.IV
收藏

基于两态Q学习的强化学习图像分类

Image Classification by Reinforcement Learning with Two-State Q-Learning

Institute of Technology, University of Kashmir(克什米尔大学理工学院)

Abdul Mueed Hafiz

摘要:

提出了一种基于深度学习和强化学习的简单高效的混合分类器。在这里,Q-Learning已经被用于两个状态和“两个或三个”动作。在文献中发现的其他技术使用从卷积神经网络提取的特征图,并在Q状态中使用这些特征图以及过去的历史。这导致这些方法中的技术困难,因为状态的数量由于特征图的大维度而很高。由于所提出的技术仅使用两个Q状态,因此它是直接的,因此具有少得多的优化参数,因此也具有简单的奖励函数。此外,与文献中发现的其他技术相比,所提出的技术使用新颖的动作来处理图像。在流行的数据库(包括ImageNet,Cats and Dogs Dataset和Caltech-101 Dataset)上,将所提出的技术的性能与其他最近的算法(如ResNet50,InceptionV3等)进行了比较。所提出的方法优于其他技术在所有使用的数据集。

英文摘要:

In this paper, a simple and efficient Hybrid Classifier is presented which is based on deep learning and reinforcement learning. Here, Q-Learning has been used with two states and 'two or three' actions. Other techniques found in the literature use feature map extracted from Convolutional Neural Networks and use these in the Q-states along with past history. This leads to technical difficulties in these approaches because the number of states is high due to large dimensions of the feature map. Because the proposed technique uses only two Q-states it is straightforward and consequently has much lesser number of optimization parameters, and thus also has a simple reward function. Also, the proposed technique uses novel actions for processing images as compared to other techniques found in literature. The performance of the proposed technique is compared with other recent algorithms like ResNet50, InceptionV3, etc. on popular databases including ImageNet, Cats and Dogs Dataset, and Caltech-101 Dataset. The proposed approach outperforms others techniques on all the datasets used.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑