检索结果-内蒙古大学图书馆

Newton design:designing CNNs with the family of Newton's methods

Science China(Information Sciences) 2023年第6期66卷 122-137页

作者： Zhengyang SHEN Yibo YANG Qi SHE Changhu WANG Jinwen MA Zhouchen LIN School of Mathematical Sciences Peking University Bytedance AI Lab JD Explore Academy Key Laboratory of Machine Perception School of Intelligence Science and TechnologyPeking University Pazhou Lab

Nowadays, convolutional neural networks(CNNs)have led the developments of machine ***, most CNN architectures are obtained by manual design, which is empirical, time-consuming, and non-transparent. In this paper, we aim at offering better insight into CNN models from the perspective of optimization theory. We propose a unified framework for understanding and designing CNN architectures with the family of Newton's methods, which is referred to as Newton design. Specifically, we observe that the standard feedforward CNN model(PlainNet)solves an optimization problem via a kind of quasi-Newton method. Interestingly, residual network(ResNet)can also be derived if we use a more general quasi-Newton method to solve this problem. Based on the above observations, we solve this problem via a better method,the Newton-conjugate-gradient(Newton-CG)method, which inspires Newton-CGNet. In the network design,we translate binary-value terms in the optimization schemes to dropout layers, so dropout modules naturally appear in the derived CNN structures with specific locations, rather than being an empirical training *** experiments on image classification and text categorization tasks verify that Newton-CGNets perform very competitively. Particularly, Newton-CGNets surpass their counterparts ResNets by over 4% on CIFAR-10 and over 10% on CIFAR-100, respectively.

关键词： CNN dropout optimization method network design Newton's method

来源：评论

学校读者我要写书评

暂无评论

Unsupervised random forest for affinity estimation

引用

Computational Visual Media 2022年第2期8卷 257-272页

作者： Yunai Yi Diya Sun Peixin Li Tae-Kyun Kim Tianmin Xu Yuru Pei Key Laboratory of Machine Perception(MOE) Department of Machine IntelligencePeking UniversityBeijing 100871China Department of Electrical and Electronic Engineering Imperial College LondonLondonUK School of Stomatology Stomatology HospitalPeking UniversityBeijing 100081China

This paper presents an unsupervised clustering random-forest-based metric for affinity estimation in large and high-dimensional *** criterion used for node splitting during forest construction can handle rank-deficiency when measuring cluster *** binary forest-based metric is extended to continuous metrics by exploiting both the common traversal path and the smallest shared parent *** proposed forest-based metric efficiently estimates affinity by passing down data pairs in the forest using a limited number of decision trees.A pseudo-leaf-splitting(PLS)algorithm is introduced to account for spatial relationships,which regularizes affinity measures and overcomes inconsistent leaf *** random-forest-based metric with PLS facilitates the establishment of consistent and point-wise *** proposed method has been applied to automatic phrase recognition using color and depth videos and point-wise *** experiments demonstrate the effectiveness of the proposed method in affinity estimation in a comparison with the state-of-the-art.

关键词： affinity estimation forest-based metric unsupervised clustering forest pseudoleaf-splitting(PLS)

来源：评论

学校读者我要写书评

暂无评论

Audio-visual keyword transformer for unconstrained sentence-level keyword spotting

引用

CAAI Transactions on intelligence Technology 2024年第1期9卷 142-152页

作者： Yidi Li Jiale Ren Yawei Wang Guoquan Wang Xia Li Hong Liu Key Laboratory of Machine Perception Peking UniversityShenzhen Graduate SchoolShenzhenChina College of Electronics and Information Engineering Sichuan UniversityChengduChina Department of Computer Science ETH ZurichZurichSwitzerland

As one of the most effective methods to improve the accuracy and robustness of speech tasks,the audio-visual fusion approach has recently been introduced into the field of keyword Spotting(KWS).However,existing audio-visual keyword spotting models are limited to detecting isolated words,while keyword spotting for unconstrained speech is still a challenging *** this end,an Audio-Visual keyword Transformer(AVKT)network is proposed to spot keywords in unconstrained video *** authors present a transformer classifier with learnable CLS tokens to extract distinctive keyword features from the variable-length audio and visual *** outputs of audio and visual branches are combined in a decision fusion *** humans can easily notice whether a keyword appears in a sentence or not,our AVKT network can detect whether a video clip with a spoken sentence contains a pre-specified ***,the position of the keyword is localised in the attention map without additional position ***-imental results on the LRS2-KWS dataset and our newly collected PKU-KWS dataset show that the accuracy of AVKT exceeded 99%in clean scenes and 85%in extremely noisy *** code is available at https://***/jialeren/AVKT.

关键词： artificial intelligence multimodal approaches natural language processing neural network speech processing

来源：评论

学校读者我要写书评

暂无评论

An Improved Algorithm for Spiking Neural Networks with Multi-Scale Attention Coding

An Improved Algorithm for Spiking Neural Networks with Multi...

引用

2024 International Conference on Cyber-Physical Social intelligence, ICCSI 2024

作者： Chen, Sisi Chen, Xiaofeng Li, Weikai Chongqing Jiaotong University Department of Mathematics Chongqing China Miit Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (纸本)9798350376739

Spiking Neural Networks (SNNs), driven by spike-based mechanisms, are known for their high efficiency and low energy consumption, which makes them ideal for applications like image classification, object detection, and medical diagnostics. However, challenges include training difficulties due to the non-differentiability of spiking activities and limitations in encoding schemes, which struggle to capture complex spatio-temporal dynamics. In this paper, we propose a novel algorithm, termed the Spatio-Temporal Backpropagation algorithm with Multi-Scale Attention Coding (STBP-MSC). STBP-MSC dynamically allocates attention across spatial and temporal domains, which improves coding efficiency and enhances the classification accuracy of SNNs. Furthermore, STBP-MSC incorporates the Complementary Leaky Integrate-and-Fire (CLIF) neuron model, which enhances temporal gradient computation. Experimental results on the MNIST and Fashion-MNIST datasets demonstrate that STBP-MSC achieves high coding efficiency and superior performance within minimal time windows. © 2024 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

UNDERSTANDING DOMAIN RANDOMIZATION FOR SIM-TO-REAL TRANSFER 10

UNDERSTANDING DOMAIN RANDOMIZATION FOR SIM-TO-REAL TRANSFER

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Chen, Xiaoyu Hu, Jiachen Jin, Chi Li, Lihong Wang, Liwei Key Laboratory of Machine Perception MOE School of Artificial Intelligence Peking University China Department of Electrical and Computer Engineering Princeton University United States Amazon Key Laboratory of Machine Perception MOE School of Artificial Intelligence Peking University International Center for Machine Learning Research Peking University China

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization-one of the most popular algorithms for sim-to-real transfer-has been demonstrated to be effective in various tasks in robotics and autonomous driving. Despite its empirical successes, theoretical understanding on why this simple algorithm works is limited. In this paper, we propose a theoretical framework for sim-to-real transfers, in which the simulator is modeled as a set of MDPs with tunable parameters (corresponding to unknown physical parameters such as friction). We provide sharp bounds on the sim-to-real gap-the difference between the value of policy returned by domain randomization and the value of an optimal policy for the real world. We prove that sim-to-real transfer can succeed under mild conditions without any real-world training samples. Our theory also highlights the importance of using memory (i.e., history-dependent policies) in domain randomization. Our proof is based on novel techniques that reduce the problem of bounding the sim-to-real gap to the problem of designing efficient learning algorithms for infinite-horizon MDPs, which we believe are of independent interest. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Gator: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose 48

Gator: Graph-Aware Transformer with Motion-Disentangled Regr...

引用

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

作者： You, Yingxuan Liu, Hong Li, Xia Li, Wenhao Wang, Ti Ding, Runwei Peking University Shenzhen Graduate School Key Laboratory of Machine Perception China ETH Zurich Department of Computer Science Switzerland

ISBN: (纸本)9781728163277

3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations during the evolution from skeleton to mesh, including joint-joint, joint-vertex and vertex-vertex relations, which often leads to implausible results. To address this issue, we propose a novel solution, called GATOR, that contains an encoder of Graph-Aware Transformer (GAT) and a decoder with Motion-Disentangled Regression (MDR) to explore these multiple relations. Specifically, GAT combines a GCN and a graph-aware self-attention in parallel to capture physical and hidden joint-joint relations. Furthermore, MDR models joint-vertex and vertex-vertex interactions to explore joint and vertex relations. Based on the clustering characteristics of vertex offset fields, MDR regresses the vertices by composing the predicted base motions. Extensive experiments show that GATOR achieves state-of-the-art performance on two challenging benchmarks. Code is available at https://***/kasvii/GATOR. © 2023 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Lighting up Oxytocin Neurons to Nurture the Brain

引用

Neuroscience Bulletin 2023年第5期39卷 866-868页

作者： Fang Zhou Junqiang Zheng Han Xu Department of Neurobiology and Department of Neurology of the Second Affiliated Hospital Zhejiang University School of MedicineHangzhou 310058China Liangzhu Laboratory MOE Frontier Science Center for Brain Science and Brain-machine IntegrationState Key Laboratory of Brain-machine IntelligenceZhejiang UniversityHangzhou 311121China NHC and CAMS Key Laboratory of Medical Neurobiology Zhejiang UniversityHangzhou 310058China

The sensory system develops earlier than the systems responsible for higher brain functions such as language and cognition[1].Moreover,sensory experiences in early life are critical for the development of the ***,how sensory experiences shape brain development is an important yet unresolved question in *** work has demonstrated that deprivation of sensory inputs in the early developmental stage causes synaptic dysfunction in the sensory ***,it has been reported that oxytocin can restore the deficits caused by somatosensory deprivation in neonatal mice,suggesting that oxytocin may play a key role in sensory-mediated synaptogenesis[2].Vision is one of the most important sensory inputs during early development in mammalians including humans[1],but the neural mechanism underlying vision-mediated brain development is still largely unknown.

关键词： neonatal neural sensory

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Mysteries of the Subcommissural Organ: A Patron Saint of Neuronal Development

引用

Neuroscience Bulletin 2024年第12期40卷 2012-2014页

作者： Yuxiang Luo Weiying Wu Zhihua Gao Department of Neurology of the Second Affiliated Hospital and School of Brain Science and Brain Medicine Zhejiang University School of MedicineHangzhou310058China Liangzhu Laboratory MOE Frontier Science Center for Brain Science and Brain-machine IntegrationState Key Laboratory of Brain-machine IntelligenceZhejiang University Medical CenterZhejiang UniversityHangzhou311121China NHC and CAMS Key Laboratory of Medical Neurobiology Zhejiang UniversityHangzhou310058China

The circumventricular organs(CVOs)are midline structures located around the third and fourth ventricles(Fig.1A).Due to the absence of the blood-brain barrier,CVOs serve as important communication sites between the brain and the cerebrospinal fluid(CSF),playing essential roles in maintaining homeostasis through blood-brain *** on their function,CVOs can be divided into two categories:sensory CVOs that sense environmental cues and transfer signals to other brain regions,and secretory CVOs that secrete hormones and glycoproteins into the blood or CSF.

关键词： organs homeostasis ventricular

来源：评论

学校读者我要写书评

暂无评论

引用

CAAI Transactions on intelligence Technology 2022年第1期7卷 26-33页

作者： Hong Liu Peipei Yuan Bing Yang Ge Yang Yang Chen Key Laboratory of Machine Perception Shenzhen Graduate SchoolPeking UniversityShenzhenChina School of Artificial Intelligence Chongqing University of TechnologyChongqingChina Yanka Kupala State University of Grodno GrodnoBelarus

Various time-frequency(T-F)masks are being applied to sound source localization ***,deep learning has dramatically advanced T-F mask ***,existing masks are usually designed for speech separation tasks and are suitable only for single-channel signals.A novel complex-valued T-F mask is proposed that reserves the head-related transfer function(HRTF),customized for binaural sound source *** addition,because the convolutional neural network that is exploited to estimate the proposed mask takes binaural spectral information as the input and output,accurate binaural cues can be *** with conventional T-F masks that emphasize single speech source–dominated T-F units,HRTFreserved masks eliminate the speech component while keeping the direct propagation ***,the estimated HRTF is capable of extracting more reliable localization features for the final direction of arrival ***,binaural sound source localization guided by the proposed T-F mask is robust under noisy and reverberant acoustic *** experimental results demonstrate that the new T-F mask is superior to conventional T-F masks and lead to the better performance of sound source localization in adverse environments.

关键词： estimation. sound function

来源：评论

学校读者我要写书评

暂无评论

Interweaved Graph and Attention Network for 3D Human Pose Estimation 48

Interweaved Graph and Attention Network for 3D Human Pose Es...

引用

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

作者： Wang, Ti Liu, Hong Ding, Runwei Li, Wenhao You, Yingxuan Li, Xia Peking University Shenzhen Graduate School Key Laboratory of Machine Perception China Eth Zürich Department of Computer Science Switzerland

ISBN: (纸本)9781728163277

Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations. To address this issue, we propose a novel Interweaved Graph and Attention Network (IGANet) that allows bidirectional communications between graph convolutional networks (GCNs) and attentions. Specifically, we introduce an IGA module, where attentions are provided with local information from GCNs and GCNs are injected with global information from attentions. Additionally, we design a simple yet effective U-shaped multi-layer perceptron (uMLP), which can capture multi-granularity information for body joints. Extensive experiments on two popular benchmark datasets (i.e. Human3.6M and MPI-INF-3DHP) are conducted to evaluate our proposed method. The results show that IGANet achieves state-of-the-art performance on both datasets. Code is available at https://***/xiu-cs/IGANet. © 2023 IEEE.

关键词： Convolution

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：