EMNAPE: efficient multi-dimensional neural architecture pruning for EdgeAI

EMNAPE: efficient multi-dimensional neural architecture pruning for EdgeAI

In this paper, we propose a multi-dimensional pruning framework, EMNAPE, to jointly prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In EMNAPE, we introduce a two-stage evaluation strategy to evalu...

Saved in:

書目詳細資料
Main Authors:	Kong, Hao, Luo, Xiangzhong, Huai, Shuo, Liu, Di, Subramaniam, Ravi, Makaya, Christian, Lin, Qian, Liu, Weichen
其他作者:	School of Computer Science and Engineering
格式:	Conference or Workshop Item
語言:	English
出版:	2023
主題:	Engineering::Computer science and engineering Heuristic Algorithms Computational Modeling
在線閱讀:	https://hdl.handle.net/10356/167488
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

相似書籍

EdgeCompress: coupling multi-dimensional model compression and dynamic inference for EdgeAI
由: Kong, Hao, et al.
出版: (2023)

Towards efficient convolutional neural network for embedded hardware via multi-dimensional pruning
由: Kong, Hao, et al.
出版: (2023)

On hardware-aware design and optimization of edge intelligence
由: Huai, Shuo, et al.
出版: (2023)

Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization
由: Huai, Shuo, et al.
出版: (2023)

Bringing AI to edge : from deep learning's perspective
由: Liu, Di, et al.
出版: (2022)

Collate: collaborative neural network learning for latency-critical edge systems
由: Huai, Shuo, et al.
出版: (2023)

EvoLP: self-evolving latency predictor for model compression in real-time edge systems
由: Huai, Shuo, et al.
出版: (2023)

EdgeNAS: discovering efficient neural architectures for edge systems
由: Luo, Xiangzhong, et al.
出版: (2023)

ZeroBN : learning compact neural networks for latency-critical edge systems
由: Huai, Shuo, et al.
出版: (2022)

Smart scissor: coupling spatial redundancy reduction and CNN compression for embedded hardware
由: Kong, Hao, et al.
出版: (2023)

HSCoNAS : hardware-software co-design of efficient DNNs via neural architecture search
由: Luo, Xiangzhong, et al.
出版: (2022)

Crossbar-aligned & integer-only neural network compression for efficient in-memory acceleration
由: Huai, Shuo, et al.
出版: (2023)

CRIMP: compact & reliable DNN inference on in-memory processing via crossbar-aligned compression and non-ideality adaptation
由: Huai, Shuo, et al.
出版: (2023)

Designing efficient DNNs via hardware-aware neural architecture search and beyond
由: Luo, Xiangzhong, et al.
出版: (2022)

SurgeNAS: a comprehensive surgery on hardware-aware differentiable neural architecture search
由: Luo, Xiangzhong, et al.
出版: (2023)

You only search once: on lightweight differentiable architecture search for resource-constrained embedded platforms
由: Luo, Xiangzhong, et al.
出版: (2023)

Work-in-progress: what to expect of early training statistics? An investigation on hardware-aware neural architecture search
由: Luo, Xiangzhong, et al.
出版: (2023)

An efficient sparse LSTM accelerator on embedded FPGAs with bandwidth-oriented pruning
由: Li, Shiqing, et al.
出版: (2023)

Enabling efficient edge intelligence: a hardware-software codesign approach
由: Huai, Shuo
出版: (2023)

EDLAB : a benchmark for edge deep learning accelerators
由: Kong, Hao, et al.
出版: (2022)

HACScale : hardware-aware compound scaling for resource-efficient DNNs
由: Kong, Hao, et al.
出版: (2022)

LAMP: load-balanced multipath parallel transmission in point-to-point NoCs
由: Chen, Hui, et al.
出版: (2022)

A comparative study of edge detection techniques for AI-based image recognition
由: Wang, Di
出版: (2020)

MUGNoC: a software-configured multicast-unicast-gather NoC for accelerating CNN dataflows
由: Chen, Hui, et al.
出版: (2023)

Implementation of edge-AI and cloud-gaming benchmarks for cloud-edge systems
由: Lim, Yan Kai
出版: (2024)

Edge AI in Internet of Things
由: Lim, Xuan Zheng
出版: (2021)

Edge AI for condition monitoring
由: Hu, Zinan
出版: (2024)

An efficient gustavson-based sparse matrix-matrix multiplication accelerator on embedded FPGAs
由: Li, Shiqing, et al.
出版: (2023)

Edge-based quality-of-service architecture
由: Lim, Teck Meng
出版: (2008)

iMAT: energy-efficient in-memory acceleration for ternary neural networks with sparse dot product
由: Zhu, Shien, et al.
出版: (2023)

Pruning in face forgery detection
由: Lam, Zhi Fah
出版: (2023)

Rethinking pruning for accelerating deep inference at the edge
由: GAO, Dawei, et al.
出版: (2020)

Neural network pruning for face anti-spoofing
由: Zhang, Yinan
出版: (2022)

Hardware-aware neural architecture search and compression towards embedded intelligence
由: Luo, Xiangzhong
出版: (2023)

Some Heuristics for the 2-Poset Cover Problem
由: Fernandez, Proceso L, Jr, et al.
出版: (2014)

TAB : unified and optimized ternary, binary and mixed-precision neural network inference on the edge
由: Zhu, Shien, et al.
出版: (2022)

Energy and area-efficient mixed-signal-based SRAM computation-in-memory for AI edge devices
由: Jo, Yongjun
出版: (2024)

Feature selection for classification applications in neural network pruning
由: Gong, Rui
出版: (2024)

Heuristic task assignment algorithm using process algebra
由: Fernandez, Kai Shan L.
出版: (1995)

Building highly efficient neural networks through weight pruning
由: Low, Xuan Hui
出版: (2022)