Search Results for author: Zhongzhi Yu

Found 12 papers, 2 papers with code

LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference

no code implementations15 Mar 2022 Zhongzhi Yu, Yonggan Fu, Shang Wu, Mengquan Li, Haoran You, Yingyan Lin

While existing works mostly fix the model precision during the whole training process, a few pioneering works have shown that dynamic precision schedules help DNNs converge to a better accuracy while leading to a lower training cost than their static precision training counterparts.

MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation

no code implementations21 Dec 2021 Zhongzhi Yu, Yonggan Fu, Sicheng Li, Chaojian Li, Yingyan Lin

ViTs are often too computationally expensive to be fitted onto real-world resource-constrained devices, due to (1) their quadratically increased complexity with the number of input tokens and (2) their overparameterized self-attention heads and model depth.

Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System

no code implementations24 Aug 2021 Gang Yu, Zhongzhi Yu, Yemin Shi, Yingshuo Wang, Xiaoqing Liu, Zheming Li, Yonggen Zhao, Fenglei Sun, Yizhou Yu, Qiang Shu

The first stage structuralizes test results by extracting relevant numerical values from clinical notes, and the disease identification stage provides a diagnosis based on text-form clinical notes and the structured data obtained from the first stage.

O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed

no code implementations17 Aug 2021 Mengquan Li, Zhongzhi Yu, Yongan Zhang, Yonggan Fu, Yingyan Lin

The recent breakthroughs and prohibitive complexities of Deep Neural Networks (DNNs) have excited extensive interest in domain-specific DNN accelerators, among which optical DNN accelerators are particularly promising thanks to their unprecedented potential of achieving superior performance-per-watt.

A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning

no code implementations11 Jun 2021 Yonggan Fu, Yongan Zhang, Chaojian Li, Zhongzhi Yu, Yingyan Lin

Driven by the explosive interest in applying deep reinforcement learning (DRL) agents to numerous real-time control and decision-making applications, there has been a growing demand to deploy DRL agents to empower daily-life intelligent devices, while the prohibitive complexity of DRL stands at odds with limited on-device resources.

Decision Making reinforcement-learning

InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks

1 code implementation22 Apr 2021 Yonggan Fu, Zhongzhi Yu, Yongan Zhang, Yifan Jiang, Chaojian Li, Yongyuan Liang, Mingchao Jiang, Zhangyang Wang, Yingyan Lin

The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices.

HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark

1 code implementation19 Mar 2021 Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Yingyan Lin

To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).

Neural Architecture Search

HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark

no code implementations ICLR 2021 Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, Yingyan Lin

To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance (e. g., energy cost and latency) of all the networks in the search space of both NAS-Bench-201 and FBNet, considering six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).

Neural Architecture Search

Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search

no code implementations24 Dec 2020 Yonggan Fu, Zhongzhi Yu, Yongan Zhang, Yingyan Lin

We therefore propose an Auto-Agent-Distiller (A2D) framework, which to our best knowledge is the first neural architecture search (NAS) applied to DRL to automatically search for the optimal DRL agents for various tasks that optimize both the test scores and efficiency.

Neural Architecture Search reinforcement-learning

Kernel Quantization for Efficient Network Compression

no code implementations11 Mar 2020 Zhongzhi Yu, Yemin Shi, Tiejun Huang, Yizhou Yu

Thus, KQ can represent the weight tensor in the convolution layer with low-bit indexes and a kernel codebook with limited size, which enables KQ to achieve significant compression ratio.

Quantization

Exploiting Partially Annotated Data in Temporal Relation Extraction

no code implementations SEMEVAL 2018 Qiang Ning, Zhongzhi Yu, Chuchu Fan, Dan Roth

As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.

Relation Extraction

Exploiting Partially Annotated Data for Temporal Relation Extraction

no code implementations18 Apr 2018 Qiang Ning, Zhongzhi Yu, Chuchu Fan, Dan Roth

As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.

Relation Extraction

Cannot find the paper you are looking for? You can Submit a new open access paper.