检索结果-内蒙古大学图书馆

10th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)

作者： Wilmot, Charles Shi, Bertram E. Triesch, Jochen Frankfurt Inst Adv Studies Frankfurt Germany Hong Kong Univ Sci & Technol Clear Water Bay Hong Kong Peoples R China

ISBN: (纸本)9781728173061

We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model follows the principle of active efficient coding (AEC), a recent extension of the classic efficient coding Hypothesis to active perception. In contrast to previous AEC models, the present model uses deep autoencoders to learn sensory representations. We also propose a new formulation of the intrinsic motivation signal that guides the learning of behavior. We demonstrate the performance of the model in simulations.

关键词： active efficient coding intrinsic motivation binocular vision vergence pursuit self-calibration autonomous learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous, self-calibrating binocular vision based on learned attention and active efficient coding 7

Autonomous, self-calibrating binocular vision based on learn...

引用

7th joint IEEE International Conference on Development Learning and Epigenetic Robotic (IEEE ICDL-EpiRob)

作者： Zhu, Qingpeng Triesch, Jochen Shi, Bertram E. Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Frankfurt Inst Adv Studies Frankfurt Germany Hong Kong Univ Sci & Technol Dept ECE Hong Kong Peoples R China Hong Kong Univ Sci & Technol Div BME Hong Kong Peoples R China

ISBN: (纸本)9781538637159

We present a self-calibrating binocular vision system that autonomously learns how to encode the visual input and how to move its eyes. The model combines the learning of disparity representations and vergence eye movements through active efficient coding (AEC) and the learning of saccades to interesting targets through two novel attention models. The first model is an extension of the Attention based on Information Maximization (AIM) model by Bruce and Tsotsos to binocular images. The second model aims to directly maximize the learning progress of the AEC model. We demonstrate that both attention models improve learning speed compared to a random gaze control strategy. Notably, the vergence eye movement controller and the two attention mechanisms controlling saccades all use the same learned sparse image encoding. The system represents a step towards building self-calibrating, infant-like robots that autonomously learn how to make sense of their environment and how to interact with it.

关键词： active efficient coding reinforcement learning saliency vergence control visual attention

来源：评论

学校读者我要写书评

暂无评论

An active efficient coding Model of Binocular Vision Development Under Normal and Abnormal Rearing Conditions 15th

An Active Efficient Coding Model of Binocular Vision Develop...

引用

15th International Conference on the Simulation of Adaptive Behavior (SAB)

作者： Klimmasch, Lukas Schneiders, Johann Lelais, Alexander Shi, Bertram E. Triesch, Jochen Frankfurt Inst Adv Studies Frankfurt Germany Hong Kong Univ Sci & Technol Hong Kong Peoples R China

ISBN: (纸本)9783319976280;9783319976273

The development of binocular vision encompasses the formation of binocular receptive fields tuned to different disparities and the calibration of accurate vergence eye movements. Experiments have shown that this development is impaired when the animal is exposed to certain abnormal rearing conditions such as growing up in an environment that is deprived of horizontal or vertical edges. Here we test the effect of abnormal rearing conditions on a recently proposed computational model of binocular development. The model is formulated in the active efficient coding framework, a generalization of classic efficient coding ideas to active perception. We show that abnormal rearing conditions lead to differences in the model's development that qualitatively match those seen in animal experiments. Furthermore, the model predicts systematic changes in vergence accuracy due to abnormal rearing. We discuss implications of the model for the treatment of developmental disorders of binocular vision such as amblyopia and strabismus.

关键词： Receptive field development Sparse coding Abnormal rearing condition active efficient coding Stereopsis Vergence

来源：评论

学校读者我要写书评

暂无评论

Autonomous learning of cyclovergence control based on active efficient coding 8

Autonomous learning of cyclovergence control based on Active...

引用

8th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)

作者： Zhu, Qingpeng Zhang, Chong Triesch, Jochen Shi, Bertram E. Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Kowloon Clear Water Bay Hong Kong Peoples R China Frankfurt Inst Adv Studies Frankfurt Germany

ISBN: (纸本)9781538661109

A central aspect of the development of visual perception is the autonomous calibration of various kinds of eye movements including saccadic, pursuit, or vergence eye movements. An important but less well-studied class of eye movements are so-called torsional eye movements, where the eyes rotate around the line of sight. In humans, such torsional eye movements obey certain lawful relationships such as Listing's Law. However, it is still an open question how these eye movements develop and what learning processes may contribute to their development. Here we propose a model of the development of torsional eye movements based on the active efficient coding (AEC) framework. AEC models the joint development of sensory encoding and movements of the sense organs to maximize the overall coding efficiency of the perceptual system. Our results demonstrate that optimizing coding efficiency in this way leads to torsional eye movements consistent with Listing's Law describing torsional eye movements in humans. This suggests that humanoid robots aiming to maximize the coding efficiency of their visual systems could also benefit from physical or simulated torsional eye movements.

关键词： torsional eye movement active efficient coding reinforcement learning Listing's law cyclovergence

来源：评论

学校读者我要写书评

暂无评论

Joint Learning of Binocularly Driven Saccades and Vergence by active efficient coding

引用

FRONTIERS IN NEUROROBOTICS 2017年第NOV期11卷 58页

作者： Zhu, Qingpeng Triesch, Jochen Shi, Bertram E. Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Hong Kong Peoples R China Frankfurt Inst Adv Studies Frankfurt Germany

This paper investigates two types of eye movements: vergence and saccades. Vergence eye movements are responsible for bringing the images of the two eyes into correspondence, whereas saccades drive gaze to interesting regions in the scene. Control of both vergence and saccades develops during early infancy. To date, these two types of eye movements have been studied separately. Here, we propose a computational model of an active vision system that integrates these two types of eye movements. We hypothesize that incorporating a saccade strategy driven by bottom-up attention will benefit the development of vergence control. The integrated system is based on the active efficient coding framework, which describes the joint development of sensory-processing and eye movement control to jointly optimize the coding efficiency of the sensory system. In the integrated system, we propose a binocular saliency model to drive saccades based on learned binocular feature extractors, which simultaneously encode both depth and texture information. Saliency in our model also depends on the current fixation point. This extends prior work, which focused on monocular images and saliency measures that are independent of the current fixation. Our results show that the proposed saliency driven saccades lead to better vergence performance and faster learning in the overall system than random saccades. Faster learning is significant because it indicates that the system actively selects inputs for the most effective learning. This work suggests that saliency-driven saccades provide a scaffold for the development of vergence control during infancy.

关键词： active efficient coding saccades vergence binocular saliency map generative adaptive subspace self-organizing map reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The Role of Contrast Sensitivity in the Development of Binocular Vision: A Computational Study 5

The Role of Contrast Sensitivity in the Development of Binoc...

引用

5th IEEE Joint International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EpiRob)

作者： Priamikov, Alexander Narayan, Vikram Shi, Bertram E. Triesch, Jochen Frankfurt Inst Adv Studies Frankfurt Germany Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781467393201

The development of accurate binocular vision relies on the acquisition of disparity tuning and the calibration of vergence eye movements. Both processes are fundamentally limited by visual acuity, which increases only gradually during the first year of life. Next to limiting performance, however, early limitations of visual acuity may also aid rapid learning analogous to Newport's "less-is-more" hypothesis. Here we use computational modeling to assess the potential impact of early acuity limitations on the development of binocular vision. Our starting point is a previous model of the development of binocular vision, formulated in the active efficient coding framework. We extend this model to incorporate the development of visual acuity between birth and 8 months. We find that the model does in fact learn faster if visual acuity starts out poor and increases with time, supporting the less-is-more hypothesis. Furthermore, we find that the speed of acuity improvement needs to be "just right", i.e., neither too rapid nor too slow for fastest learning. Overall, our model suggests that early limitations of visual acuity may aid infants in acquiring binocular vision skills and it provides a good starting point for computational modeling of developmental disorders of binocular vision.

关键词： binocular vision contrast sensitivity function disparity tuning vision development vergence eye movements active efficient coding efficient coding

来源：评论

学校读者我要写书评

暂无评论

Self-Calibrating Saccade-Vergence Interactions

Self-Calibrating Saccade-Vergence Interactions

引用

IEEE International Conference on Development and Learning (ICDL)

作者： Lopez, Francisco M. Raabe, Marcel C. Shi, Bertram E. Triesch, Jochen Frankfurt Inst Adv Studies Frankfurt Germany Xidian FIAS Int Joint Res Ctr Frankfurt Germany Hong Kong Univ Sci & Technol Clear Water Bay Hong Kong Peoples R China

ISBN: (纸本)9798350348569;9798350348552

Binocular saccades in the three-dimensional world entail changes in the direction and depth of gaze. Newborns must autonomously learn to control these two types of eye movements concurrently. Here, we put forward a computational model of the joint development of conjugate saccades and vergence, resulting in the self-calibration of disjunctive saccades. This work builds on principles of information theory and efficient coding. We propose that conjugate saccades and vergence are learned together with the shared motivation of maximizing the mutual information between binocular visual inputs and their neural representations. We train and evaluate our model using an infant embodiment in a simulated playroom. Our results are compatible with experimental evidence and show that vergence predicts the binocular disparity at the target of a saccade.

关键词： Binocular vision Disjunctive saccades Saccade-vergence interactions active efficient coding

来源：评论

学校读者我要写书评

暂无评论

Robot End Effector Tracking Using Predictive Multisensory Integration

引用

FRONTIERS IN NEUROROBOTICS 2018年第October期12卷 66页

作者： Wijesinghe, Lakshitha P. Triesch, Jochen Shi, Bertram E. Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Kowloon Hong Kong Peoples R China Frankfurt Inst Adv Studies Frankfurt Germany

We propose a biologically inspired model that enables a humanoid robot to learn how to track its end effector by integrating visual and proprioceptive cues as it interacts with the environment. A key novel feature of this model is the incorporation of sensorimotor prediction, where the robot predicts the sensory consequences of its current bodymotion as measured by proprioceptive feedback. The robot develops the ability to perform smooth pursuit-like eye movements to track its hand, both in the presence and absence of visual input, and to track exteroceptive visual motions. Our framework makes a number of advances over past work. First, our model does not require a fiducial marker to indicate the robot hand explicitly. Second, it does not require the forward kinematics of the robot arm to be known. Third, it does not depend upon pre-defined visual feature descriptors. These are learned during interaction with the environment. We demonstrate that the use of prediction in multisensory integration enables the agent to incorporate the information from proprioceptive and visual cues better. The proposed model has properties that are qualitatively similar to the characteristics of human eye-hand coordination.

关键词： active efficient coding developmental robotics sensorimotor prediction generative adaptive subspace self-organizing map reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：