检索结果-内蒙古大学图书馆

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Wang, Zongwu Liu, Fangxin Yang, Ning Huang, Shiyuan Li, Haomin Jiang, Li Shanghai Jiao Tong University Department of Computer Science and Engineering China Shanghai Qi Zhi Institute China AI Institute Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence China

ISBN: (纸本)9798350350579

Brain-inspired spiking neural networks (SNNs) are considered energy-efficient alternatives to conventional deep neural networks (DNNs). By adopting event-driven information processing, SNNs can significantly reduce the computational demands associated with DNNs, while still achieving comparable performance. However, current SNNs primarily prioritize high accuracy by constructing complex neuron models that generate sparse spikes. Unfortunately, this approach results in low energy efficiency and high latency, posing a significant challenge for deploying SNNs at the edge. Furthermore, the dominant computation in SNNs, which involves spike-wise Accumulate-Compare operations, is well-suited for Computing-in-Memory (CIM) architectures. However, exploiting high parallel processing and spike sparsity in CIM-based SNN accelerators is challenging due to the irregularity and time dependency of spikes. To address these limitations, the paper proposes COMPASS, a SRAM-based CIM architecture for efficient SNNs. We first introduce an efficient method to exploit irregular sparsity for both input spikes (explicit) and output spikes (implicit). This is achieved through a speculation mechanism that exploit dynamic spike patterns, enabling lean hardware for sparsity utilization. Additionally, the CIM architecture is carefully modified to facilitate dynamic spike pattern generation and exploitation with minimal overhead. Moreover, we design an adaptive dataflow with temporal spike representation tailored for input/output spikes, reducing memory footprint and enabling parallel execution. Comprehensive evaluation results demonstrate that COMPASS can achieve 26.7x end-to-end speedup over recent SNN accelerators hardware implementation with up to 386.7x less energy per inference. © 2024 IEEE.

关键词： Compasses (magnetic)

来源：评论

学校读者我要写书评

暂无评论

Going beyond linear mode connectivity: the layerwise linear feature connectivity 23

Going beyond linear mode connectivity: the layerwise linear ...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zhanpeng Zhou Yongyi Yang Xiaojiang Yang Junchi Yan Wei Hu Dept. of Computer Science and Engineering & MoE Key Lab of AI Shanghai Jiao Tong University Dept. of Electrical Engineering & Computer Science University of Michigan

Recent work has revealed many intriguing empirical phenomena in neural network training, despite the poorly understood and highly complex loss landscapes and training dynamics. One of these phenomena, Linear Mode Connectivity (LMC), has gained considerable attention due to the intriguing observation that different solutions can be connected by a linear path in the parameter space while maintaining near-constant training and test losses. In this work, we introduce a stronger notion of linear connectivity, Layerwise Linear Feature Connectivity (LLFC), which says that the feature maps of every layer in different trained networks are also linearly connected. We provide comprehensive empirical evidence for LLFC across a wide range of settings, demonstrating that whenever two trained networks satisfy LMC (via either spawning or permutation methods), they also satisfy LLFC in nearly all the layers. Furthermore, we delve deeper into the underlying factors contributing to LLFC, which reveal new insights into the permutation approaches. The study of LLFC transcends and advances our understanding of LMC by adopting a feature-learning perspective. We released our source code at https://***/zzp1012/LLFC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Discriminator and Transfer Based Fast Domain Adaptation For End-To-End Speech Recognition 48

Joint Discriminator and Transfer Based Fast Domain Adaptatio...

引用

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

作者： Shao, Hang Tan, Tian Wang, Wei Gong, Xun Qian, Yanmin Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai China AISpeech Ltd Suzhou China

ISBN: (纸本)9781728163277

Adapting End-to-End (E2E) models to unseen domains is still a big challenge since training E2E models requires lots of paired audio and text training data. We propose a novel domain adaptation framework for the E2E model, which only uses the text of the target domain. Moreover, the proposed methods can keep the performance on the source domain intact while greatly improving the performance on the target domain. The proposed framework consists of two parts: the discriminator and the transfer which were optimized separately. Finally, optimized discriminator and transfer were combined and evaluated on two domain adaption tasks. In the experiments of adapting the English Librispeech to Gigaspeech, we obtained an average relative 11.6% and 11.8% on word error rate (WER) reduction for the target domain dev and test sets, respectively, while almost without WER degradation on the source domain. For the inhouse Chinese corpus aviation and TV, the character error rate (CER) of the source domain increased within 5%, while the CER on the target domain achieved around relative 85% and 42% improvement, respectively. In addition, our approach is also more effective in the mixed domain scenarios in the evaluation. © 2023 IEEE.

关键词： discriminator and transfer domain adaptation end-to-end speech recognition log-likelihood ratio

来源：评论

学校读者我要写书评

暂无评论

Target Sound Extraction with Variable Cross-Modality Clues 48

Target Sound Extraction with Variable Cross-Modality Clues

引用

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

作者： Li, Chenda Qian, Yao Chen, Zhuo Wang, Dongmei Yoshioka, Takuya Liu, Shujie Qian, Yanmin Zeng, Michael Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-LANCE Lab Department of Computer Science and Engineering China Microsoft RedmondWA United States

ISBN: (纸本)9781728163277

Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form of target sound clues, such as a sound class label, which limits the ways in which users can interact with the model to specify the target sounds. To leverage variable number of clues cross modalities available in the inference phase, including a video, a sound event class, and a text caption, we propose a unified transformer-based TSE model architecture, where a multi-clue attention module integrates all the clues across the modalities. Since there is no off-the-shelf benchmark to evaluate our proposed approach, we build a dataset1 based on public corpora, Audioset and AudioCaps. Experimental results for seen and unseen target-sound evaluation sets show that our proposed TSE model can effectively deal with a varying number of clues which improves the TSE performance and robustness against partially compromised clues. © 2023 IEEE.

关键词： cross-modality attention multi-clue processing Target sound extraction

来源：评论

学校读者我要写书评

暂无评论

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning 38

Making Offline RL Online: Collaborative World Models for Off...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Qi Yang, Junming Wang, Yunbo Jin, Xin Zeng, Wenjun Yang, Xiaokang MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Ningbo Institute of Digital Twin Eastern Institute of Technology China School of Computer Science and Engineering Southeast University China

Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the overestimation bias by encouraging conservative behaviors. This paper, in contrast, tries to build more flexible constraints for value estimation without impeding the exploration of potential advantages. The key idea is to leverage off-the-shelf RL simulators, which can be easily interacted with in an online manner, as the "test bed" for offline policies. To enable effective online-to-offline knowledge transfer, we introduce CoWorld, a model-based RL approach that mitigates cross-domain discrepancies in state and reward spaces. Experimental results demonstrate the effectiveness of CoWorld, outperforming existing RL approaches by large margins. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning

Circuit Design and Efficient Simulation of Quantum Inner Pro...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Hao Xiong Yehui Tang Xinyu Ye Junchi Yan Department of Computer Science and Engineering MoE Key Lab of AI Shanghai Jiao Tong University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

For the essential operation, namely inner product (IP) as widely adopted in classic computing e.g. matrix multi-plication, its quantum counterpart: quantum inner product (QIP), has also been recently theoretically explored with a verifiable lower complexity on quantum computers. How-ever, it remains unclear for the embodiment of the quantum circuits (QC) for QIP, let alone a (thorough) evaluation of the QIP circuits, especially in a practical context in the NISQ era by applying QIP to ML via hybrid quantum-classic pipelines. In this paper, we carefully design the QIP circuits from scratch, whose complexity is in accordance with the theoretical complexity. To make the simulation tractable on classic computers, especially when it is integrated in the gradient-based hybrid ML pipelines, we further devise a highly-efficient simulation scheme by directly simulates the output state. Experiments show that the scheme acceler-ates the simulation for more than 68k times compared with the previous circuit simulator. This allows our empirical evaluation on typical machine learning tasks, ranging from supervised and self-supervised learning via neural nets, to K-Means clustering. The results show that the calculation error brought by typical quantum mechanisms would incur in general little influence on the final numerical results given sufficient qubits. However, certain tasks e.g. ranking in K-Means could be more sensitive to quantum noise.

关键词： computers Pipelines Qubit Quantum mechanics Machine learning Self-supervised learning Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition 48

Front-End Adapter: Adapting Front-End Input of Speech Based ...

引用

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

作者： Chen, Xie Ma, Ziyang Tang, Changli Wang, Yujin Zheng, Zhisheng Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-Lance Lab Department of Computer Science and Engineering Shanghai China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9781728163277

Recent years have witnessed a boom in self-supervised learning (SSL) in various areas including speech processing. Speech based SSL models present promising performance in a range of speech related tasks. However, the training of SSL models is computationally expensive and a common practice is to fine-tune a released SSL model on the specific task. It is essential to use consistent front-end input during pre-training and fine-tuning. This consistency may introduce potential issues when the optimal front-end is not the same as that used in pre-training. In this paper, we propose a simple but effective front-end adapter to address this front-end discrepancy. By minimizing the distance between the outputs of different front-ends, the filterbank feature (Fbank) can be compatible with SSL models which are pre-trained with waveform. The experiment results demonstrate the effectiveness of our proposed front-end adapter on several popular SSL models for the speech recognition task. © 2023 IEEE.

关键词： Adapter Automatic Speech Recognition Front-end Feature Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Boosting Order-Preserving and Transferability for Neural Architecture Search: A Joint Architecture Refined Search and Fine-Tuning Approach

Boosting Order-Preserving and Transferability for Neural Arc...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Beichen Zhang Xiaoxing Wang Xiaohan Qin Junchi Yan Department of Computer Science and Engineering & MoE Key Lab of AI Shanghai Jiao Tong University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Supernet is a core component in many recent Neural Architecture Search (NAS) methods. It not only helps embody the search space but also provides a (relative) estimation of the final performance of candidate architectures. Thus, it is critical that the top architectures ranked by a supernet should be consistent with those ranked by true performance, which is known as the order-preserving ability. In this work, we analyze the order-preserving ability on the whole search space (global) and a sub-space of top architectures (local), and empirically show that the local order-preserving for current two-stage NAS methods still need to be improved. To rectify this, we propose a novel concept of Supernet Shifting, a refined search strategy combining architecture searching with supernet fine-tuning. Specifically, apart from evaluating, the training loss is also accumulated in searching and the supernet is updated every iteration. Since superior architectures are sampled more frequently in evolutionary searching, the supernet is encouraged to focus on top architectures, thus improving local order-preserving. Besides, a pre-trained supernet is often un-reusable for one-shot methods. We show that Supernet Shifting can fulfill transferring supernet to a new dataset. Specifically, the last classifier layer will be unset and trained through evolutionary searching. Comprehensive experiments show that our method has better order-preserving ability and can find a dominating architecture. Moreover, the pre-trained supernet can be easily transferred into a new dataset with no loss of performance.

关键词： Training computer vision Estimation computer architecture Search problems Boosting Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

CAM-GUI: A Conversational Assistant on Mobile GUI 18th

CAM-GUI: A Conversational Assistant on Mobile GUI

引用

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Zhu, Zichen Sun, Liangtai Yang, Jingkai Peng, Yifan Zou, Weilin Li, Ziyuan Li, Wutao Chen, Lu Ma, Yingzi Zhang, Danyang Fan, Shuai Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Sichuan University Sichuan Chengdu China AISpeech Ltd. Suzhou China

ISBN: (纸本)9789819706006

Smartphone assistants are becoming more and more popular in our daily lives. These assistants mostly rely on the API-based Task-Oreiented Dialogue (TOD) systems, which limits the generality of these assistants, and the development of APIs would cost much labor and time. In this paper, we develop a Conversational Assistant on Mobile GUI (CAM-GUI), which can directly perform GUI operations on real devices, without the need of TOD-related backend APIs. To evaluate the performance of our assistant, we collect a dataset containing dialogues and GUI operation traces. From the experiment demonstrations and user studies, we show that the CAM-GUI reaches promising results. Our system demonstration can be downloaded from this link. You can watch our demo through this link. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach

arXiv

引用

arXiv 2024年

作者： Zhang, Beichen Wang, Xiaoxing Qin, Xiaohan Yan, Junchi Department of Computer Science and Engineering MoE Key Lab of AI Shanghai Jiao Tong University China

关键词： Iterative methods

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：