Search

Your search keyword '"Guobin, Shen"' showing total 281 results
Start Over Author "Guobin, Shen"
281 results on '"Guobin, Shen"'

9. Brain-inspired and Self-based Artificial Intelligence.

Author

Yi Zeng 0001, Feifei Zhao, Yuxuan Zhao, Dongcheng Zhao, Enmeng Lu, Qian Zhang 0080, Yuwei Wang, Hui Feng, Zhuoya Zhao, Jihang Wang, Qingqun Kong, Yinqian Sun, Yang Li 0141, Guobin Shen, Bing Han, Yiting Dong, Wenxuan Pan, Xiang He, Aorigele Bao, and Jin Wang

Published
2024
Full Text
View/download PDF

32. Backpropagation with biologically plausible spatiotemporal adjustment for training deep spiking neural networks

Author

Guobin Shen, Dongcheng Zhao, and Yi Zeng

Subjects
DSML2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem, Computer software, QA76.75-76.765
Abstract

Summary: The spiking neural network (SNN) mimics the information-processing operation in the human brain. Directly applying backpropagation to the training of the SNN still has a performance gap compared with traditional deep neural networks. To address the problem, we propose a biologically plausible spatial adjustment that rethinks the relationship between membrane potential and spikes and realizes a reasonable adjustment of gradients to different time steps. It precisely controls the backpropagation of the error along the spatial dimension. Secondly, we propose a biologically plausible temporal adjustment to make the error propagate across the spikes in the temporal dimension, which overcomes the problem of the temporal dependency within a single spike period of traditional spiking neurons. We have verified our algorithm on several datasets, and the experimental results have shown that our algorithm greatly reduces network latency and energy consumption while also improving network performance. The bigger picture: The spiking neural network (SNN) captures more important aspects of brain information processing and has been applied to various domains. The biggest problem restricting the development of SNN is the training algorithm. Backpropagation (BP)-based training has extended SNNs to more complex network structures and datasets. However, the traditional design of BP ignores the dynamic characteristics of SNNs and is not biologically plausible. This paper rethinks the problems in BP-based SNNs and proposes a biologically plausible spatiotemporal adjustment to replace the traditional artificial design. The adjustment greatly improves the performance of the SNNs and reduces energy consumption and latency. The long-term ambition of this research is to take more inspiration on learning mechanisms and structures from the cognitive brain at different levels of details to build even more biologically plausible SNNs as a foundation for future artificial intelligence models.

Published
2022
Full Text
View/download PDF

43. LIMU-BERT

Author

Huatao Xu, Guobin Shen, Mo Li, Rui Tan, and Pengfei Zhou

Subjects
Sensing applications, business.industry, Computer science, Deep learning, Activity recognition, Inertial measurement unit, Feature (machine learning), General Earth and Planetary Sciences, Computer vision, Artificial intelligence, business, Feature learning, Mobile device, Natural language, General Environmental Science
Abstract

Deep learning greatly empowers Inertial Measurement Unit (IMU) sensors for various mobile sensing applications, including human activity recognition, human-computer interaction, localization and tracking, and many more. Most existing works require substantial amounts of well-curated labeled data to train IMU-based sensing models, which incurs high annotation and training costs. Compared with labeled data, unlabeled IMU data are abundant and easily accessible. In this work, we present LIMU-BERT, a novel representation learning model that can make use of unlabeled IMU data and extract generalized rather than task-specific features. LIMU-BERT adopts the principle of self-supervised training of the natural language model BERT to effectively capture temporal relations and feature distributions in IMU sensor measurements. However, the original BERT is not adaptive to mobile IMU data. By meticulously observing the characteristics of IMU sensors, we propose a series of techniques and accordingly adapt LIMU-BERT to IMU sensing tasks. The designed models are lightweight and easily deployable on mobile devices. With the representations learned via LIMU-BERT, task-specific models trained with limited labeled samples can achieve superior performances. We extensively evaluate LIMU-BERT with four open datasets. The results show that the LIMU-BERT enhanced models significantly outperform existing approaches in two typical IMU sensing applications.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results