检索结果-内蒙古大学图书馆

4th International Workshop on Human Brain and Artificial Intelligence, HBAI 2024

作者： Zhou, Zhou He, Guohang Zhang, Zheng Leng, Luziwei Guo, Qinghai Liao, Jianxing Song, Xuan Cheng, Ran Southern University of Science and Technology Shenzhen518055 China Advanced Computing and Storage Lab Huawei Technologies Co. Ltd. Shenzhen518055 China

ISBN: (纸本)9789819640003

Traditional invasive Brain-Computer Interfaces (iBCIs) typically depend on neural decoding processes conducted on workstations within laboratory settings, which prevents their everyday usage. Implementing these decoding processes on edge devices, such as the wearables, introduces considerable challenges related to computational demands, processing speed, and maintaining accuracy. This study seeks to identify an optimal neural decoding backbone that boasts robust performance and swift inference capabilities suitable for edge deployment. We executed a series of neural decoding experiments involving nonhuman primates engaged in random reaching tasks, evaluating four prospective models, Gated Recurrent Unit (GRU), Transformer, Receptance Weighted Key Value (RWKV), and Selective State Space model (Mamba), across several metrics: single-session decoding, multi-session decoding, new session fine-tuning, inference speed, calibration speed, and scalability. The findings indicate that although the GRU model delivers sufficient accuracy, the RWKV and Mamba models are preferable due to their superior inference and calibration speeds. Additionally, RWKV and Mamba comply with the scaling law, demonstrating improved performance with larger data sets and increased model sizes, whereas GRU shows less pronounced scalability, and the Transformer model requires computational resources that scale prohibitively. This paper presents a thorough comparative analysis of the four models in various scenarios. The results are pivotal in pinpointing an optimal backbone that can handle increasing data volumes and is viable for edge implementation. This analysis provides essential insights for ongoing research and practical applications in the field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

arXiv

引用

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

SpikingMiniLM: energy-efficient spiking transformer for natural language understanding

引用

Science China(Information Sciences) 2024年第10期67卷 115-128页

作者： Jiayu ZHANG Jiangrong SHEN Zeke WANG Qinghai GUO Rui YAN Gang PAN Huajin TANG College of Computer Science and Technology Zhejiang University The State Key Lab of Brain-Machine Intelligence Zhejiang University Collaborative Innovation Center of Artificial Intelligence Zhejiang University Advanced Computing and Storage Laboratory Huawei Technologies Co. Ltd. College of Computer Science and Technology Zhejiang University of Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University

In the era of large-scale pretrained models, artificial neural networks（ANNs） have excelled in natural language understanding（NLU） tasks. However, their success often necessitates substantial computational resources and energy consumption. To address this, we explore the potential of spiking neural networks（SNNs） in NLU——a promising avenue with demonstrated advantages, including reduced power consumption and improved efficiency due to their event-driven characteristics. We propose the SpikingMiniLM,a novel spiking Transformer model tailored for natural language understanding. We first introduce a multi-step encoding method to convert text embeddings into spike trains. Subsequently, we redesign the attention mechanism and residual connections to make our model operate on the pure spike-based paradigm without any normalization technique. To facilitate stable and fast convergence, we propose a general parameter initialization method grounded in the stable firing rate principle. Furthermore, we apply an ANN-to-SNN knowledge distillation to overcome the challenges of pretraining SNNs. Our approach achieves a macro-average score of 75.5 on the dev sets of the GLUE benchmark, retaining 98% of the performance exhibited by the teacher model MiniLMv2. Our smaller model also achieves similar performance to BERTMINIwith fewer parameters and much lower energy consumption, underscoring its competitiveness and resource efficiency in NLU tasks.

关键词： spiking neural networks natural language understanding spiking Transformer spike-based attention multi-step encoding ANN-to-SNN distillation

来源：评论

学校读者我要写书评

暂无评论

Video Interpolation by Event-driven Anisotropic Adjustment of Optical Flow

arXiv

引用

arXiv 2022年

作者： Wu, Song You, Kaichao He, Weihua Yang, Chen Tian, Yang Wang, Yaoyuan Zhang, Ziyang Liao, Jianxing Advanced Computing and Storage Lab Huawei Technologies Co. Ltd China Tsinghua University China

Video frame interpolation is a challenging task due to the ever-changing real-world scene. Previous methods often calculate the bidirectional optical flows and then predict the intermediate optical flows under the linear motion assumptions, leading to isotropic intermediate flow generation. Follow-up research obtained anisotropic adjustment through estimated higher-order motion information with extra frames. Based on the motion assumptions, their methods are hard to model the complicated motion in real scenes. In this paper, we propose an end-to-end training method A2OF for video frame interpolation with event-driven Anisotropic Adjustment of Optical Flows. Specifically, we use events to generate optical flow distribution masks for the intermediate optical flow, which can model the complicated motion between two frames. Our proposed method outperforms the previous methods in video frame interpolation, taking supervised event-based video interpolation to a higher stage. © 2022, CC BY-NC-ND.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Hub-pathway: transfer learning from a hub of pre-trained models 22

Hub-pathway: transfer learning from a hub of pre-trained mod...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Yang Shu Zhangjie Cao Ziyang Zhang Jianmin Wang Mingsheng Long School of Software BNRist Tsinghua University China Advanced Computing and Storage Lab Huawei Technologies Co. Ltd

ISBN: (纸本)9781713871088

Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with the emergence of deep models pre-trained from different resources, model hubs consisting of diverse models with various architectures, pre-trained datasets and learning paradigms are available. Directly applying single-model transfer learning methods to each model wastes the abundant knowledge of the model hub and suffers from high computational cost. In this paper, we propose a Hub-Pathway framework to enable knowledge transfer from a model hub. The framework generates data-dependent pathway weights, based on which we assign the pathway routes at the input level to decide which pre-trained models are activated and passed through, and then set the pathway aggregation at the output level to aggregate the knowledge from different models to make predictions. The proposed framework can be trained end-to-end with the target task-specific loss, where it learns to explore better pathway configurations and exploit the knowledge in pre-trained models for each target datum. We utilize a noisy pathway generator and design an exploration loss to further explore different pathways throughout the model hub. To fully exploit the knowledge in pre-trained models, each model is further trained by specific data that activate it, which ensures its performance and enhances knowledge transfer. Experiment results on computer vision and reinforcement learning tasks demonstrate that the proposed Hub-Pathway framework achieves the state-of-the-art performance for model hub transfer learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models

arXiv

引用

arXiv 2022年

作者： Shu, Yang Cao, Zhangjie Zhang, Ziyang Wang, Jianmin Long, Mingsheng School of Software BNRist Tsinghua University China Advanced Computing and Storage Lab Huawei Technologies Co. Ltd China

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation

arXiv

引用

arXiv 2023年

作者： Wang, Dongsheng Jia, Xu Zhang, Yang Zhang, Xinyu Wang, Yaoyuan Zhang, Ziyang Wang, Dong Lu, Huchuan School of Artificial Intelligence Dalian University of Technology China Advanced Computing and Storage Lab Huawei Technologies Co. Ltd China

Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner. Compared with frame-based sensors, event cameras have microsecond-level latency and high dynamic range, hence showing great potential for object detection under high-speed motion and poor illumination conditions. Due to sparsity and asynchronism nature with event streams, most of existing approaches resort to hand-crafted methods to convert event data into 2D grid representation. However, they are sub-optimal in aggregating information from event stream for object detection. In this work, we propose to learn an event representation optimized for event-based object detection. Specifically, event streams are divided into grids in the x-y-t coordinates for both positive and negative polarity, producing a set of pillars as 3D tensor representation. To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection. Long memory is encoded in the hidden state of adaptive convLSTMs while short memory is modeled by computing spatial-temporal correlation between event pillars at neighboring time intervals. Extensive experiments on the recently released event-based automotive detection dataset demonstrate the effectiveness of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ranking and tuning pre-trained models: a new paradigm for exploiting model hubs

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 9400-9446页

作者： Kaichao You Yong Liu Ziyang Zhang Jianmin Wang Michael I. Jordan Mingsheng Long School of Software BNRist Tsinghua University Beijing China Advanced Computing and Storage Lab Huawei Technologies Co. Ltd Division of Computer Science and Department of Statistics UC Berkeley CA

Model hubs with many pre-trained models (PTMs) have become a cornerstone of deep learning. Although built at a high cost, they remain under-exploited--practitioners usually pick one PTM from the provided model hub by popularity and then fine-tune the PTM to solve the target task. This naïve but common practice poses two obstacles to full exploitation of pre-trained model hubs: first, the PTM selection by popularity has no optimality guarantee, and second, only one PTM is used while the remaining PTMs are ignored. An alternative might be to consider all possible combinations of PTMs and extensively fine-tune each combination, but this would not only be prohibitive computationally but may also lead to statistical over-fitting. In this paper, we propose a new paradigm for exploiting model hubs that is intermediate between these extremes. The paradigm is characterized by two aspects: (1) We use an evidence maximization procedure to estimate the maximum value of label evidence given features extracted by pre-trained models. This procedure can rank all the PTMs in a model hub for various types of PTMs and tasks before fine-tuning. (2) The best ranked PTM can either be fine-tuned and deployed if we have no preference for the model's architecture or the target PTM can be tuned by the top K ranked PTMs via a Bayesian procedure that we propose. This procedure, which we refer to as B-Tuning, not only improves upon specialized methods designed for tuning homogeneous PTMs, but also applies to the challenging problem of tuning heterogeneous PTMs where it yields a new level of benchmark performance.

关键词： pre-trained model hub model ranking model tuning transfer learning

来源：评论

学校读者我要写书评

暂无评论

Short-Term Plasticity Neurons Learning to Learn and Forget

arXiv

引用

arXiv 2022年

作者： Rodriguez, Hector Garcia Guo, Qinghai Moraitis, Timoleon Huawei Technologies Zurich Research Center Switzerland University College London United Kingdom Advanced Computing & Storage Lab Huawei Technologies Shenzhen China

Short-term plasticity (STP) is a mechanism that stores decaying memories in synapses of the cerebral cortex. In computing practice, STP has been used, but mostly in the niche of spiking neurons, even though theory predicts that it is the optimal solution to certain dynamic tasks. Here we present a new type of recurrent neural unit, the STP Neuron (STPN), which indeed turns out strikingly powerful. Its key mechanism is that synapses have a state, propagated through time by a self-recurrent connection-within-the-synapse. This formulation enables training the plasticity with backpropagation through time, resulting in a form of learning to learn and forget in the short term. The STPN outperforms all tested alternatives, i.e. RNNs, LSTMs, other models with fast weights, and differentiable plasticity. We confirm this in both supervised and reinforcement learning (RL), and in tasks such as Associative Retrieval, Maze Exploration, Atari video games, and MuJoCo robotics. Moreover, we calculate that, in neuromorphic or biological circuits, the STPN minimizes energy consumption across models, as it depresses individual synapses dynamically. Based on these, biological STP may have been a strong evolutionary attractor that maximizes both efficiency and computational power. The STPN now brings these neuromorphic advantages also to a broad spectrum of machine learning practice. Code is available at https://***/Neuromorphiccomputing/stpn. Copyright © 2022, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Audio-Driven High Definetion and Lip-Synchronized Talking Face Generation Based on Face Reenactment 48

Audio-Driven High Definetion and Lip-Synchronized Talking Fa...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Xianyu Zhang, Yuhan He, Weihua Wang, Yaoyuan Li, Minglei Wang, Yuchen Zhang, Jingyi Zhou, Shunbo Zhang, Ziyang Huawei Technologies Co. Ltd. Advanced Computing and Storage Lab China Huawei Technologies Co. Ltd. Language & Speech Innovation Lab China Huawei Technologies Co. Ltd. Nce Dept. China Huawei Technologies Co. Ltd. Ascend Lab China Huawei Technologies Co. Ltd. Edge Cloud Innovation Lab China

ISBN: (纸本)9781728163277

Generating audio-driven photo-realistic talking face has received intensive attention due to its ability to bring more new human-computer interaction experiences. However, previous works struggled to balance high definition, lip synchronization, and low customization costs, which would degrade the user experience. In this paper, a novel audio-driven talking face generation method was proposed, which subtly converts the problem of improving video definition into the problem of face reenactment to produce both lip-synchronized and high- definition face video. The framework is decoupled, meaning that the same trained model can be used on arbitrary characters and audio without further customizing training for specific people, thus significantly reducing costs. Experiment results show that our proposed method achieves the high video definition, and comparable lip synchronization performance with the existing state-of-the-art methods. © 2023 IEEE.

关键词： Human computer interaction

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：