首页> 外文会议>The Fourth joint IEEE international conferences on development and learning and epigenetic robotics >Incremental training of Restricted Boltzmann Machines using information driven saccades
【24h】

Incremental training of Restricted Boltzmann Machines using information driven saccades

机译:使用信息驱动扫视镜对受限玻尔兹曼机进行增量训练

获取原文
获取原文并翻译 | 示例

摘要

In the context of developmental robotics, a robot has to cope with complex sensorimotor spaces by reducing their dimensionality. In the case of sensor space reduction, classical approaches for pattern recognition use either hardcoded feature detection or supervised learning. We believe supervised learning and hard-coded feature extraction must be extended with unsupervised learning of feature representations. In this paper, we present an approach to learn representations using space-variant images and saccades. The saccades are driven by a measure of quantity of information in the visual scene, emerging from the activations of Restricted Boltzmann Machines (RBMs). The RBM, a generative model, is trained incrementally on locations where the system saccades. Our approach is implemented using real data captured by a NAO robot in indoor conditions.
机译:在发展型机器人技术的背景下,机器人必须通过减小尺寸来应对复杂的感觉运动空间。在减少传感器空间的情况下,用于模式识别的经典方法使用硬编码特征检测或监督学习。我们认为,必须在无监督学习特征表示的情况下扩展监督学习和硬编码特征提取。在本文中,我们提出了一种使用空间变量图像和扫视图像来学习表示的方法。扫视由视觉场景中一定数量的信息所驱动,这些信息是由受限玻尔兹曼机器(RBM)的激活产生的。 RBM是一种生成模型,在系统搜寻的位置上进行增量培训。我们的方法是使用NAO机器人在室内条件下捕获的真实数据来实现的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号