Expectation Learning and Crossmodal Modulation with a Deep Adversarial Network

doi:10.1109/IJCNN.2018.8489303

	Expectation Learning and Crossmodal Modulation with a Deep Adversarial Network
	Barros, Pablo 1; Parisi, German I.1; Fu, Di 2,3; Liu, Xun2,3 ; Wermter, Stefan 1
	2018-10-01
会议名称	2018 International Joint Conference on Neural Networks, IJCNN 2018
会议录名称	Proceedings of the International Joint Conference on Neural Networks
会议日期	July 8, 2018 - July 13, 2018
会议地点	Rio de Janeiro, Brazil
会议举办国	Brazil
出版者	Institute of Electrical and Electronics Engineers Inc.
产权排序	2
摘要	The human brain is able to learn, generalize, and predict crossmodal stimuli which help us to understand the world around us. Some characteristics of crossmodal learning inspired some computational models but most of the solutions only go as far as to implement strategies for early or late crossmodal fusion. In this paper, we propose the use of two mechanisms from behavioral psychology to enhance the capabilities of a deep adversarial network to learn crossmodal stimuli: The unity assumption modulation and expectation learning. We use real-world data to train and evaluate our model in a set of experiments and demonstrate how these mechanisms affect the learning behavior of the model and how they contribute to making it learn crossmodal coincident stimuli. Our experiments show that the addition of these two mechanisms modulates the crossmodal binding capabilities of the model and improves the learning of unisensory descriptors. © 2018 IEEE.
学科领域	Behavioral Research
DOI	10.1109/IJCNN.2018.8489303
收录类别	EI
语种	英语
EI主题词	Modulation
引用统计
文献类型	会议论文
条目标识符	https://ir.psych.ac.cn/handle/311026/27743
专题	中国科学院行为科学重点实验室
作者单位	1.Knowledge Technology, Department of Informatics, University of Hamburg, Hamburg, Germany; 2.CAS Key Laboratory of Behavioral Science, Institute of Psychology, Beijing, China; 3.Department of Psychology, University of Chinese Academy of Sciences, Beijing, China
推荐引用方式 GB/T 7714	Barros, Pablo,Parisi, German I.,Fu, Di,et al. Expectation Learning and Crossmodal Modulation with a Deep Adversarial Network[C]:Institute of Electrical and Electronics Engineers Inc.,2018.