7,612 Hits in 3.9 sec

Coarse grain parallelization of deep neural networks

Marc Gonzalez Tallada
2016 Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP '16  
This paper describes the implementation and analysis of a network-agnostic and convergence-invariant coarse-grain parallelization of the DNN training algorithm.  ...  Deep neural networks (DNN) have recently achieved extraordinary results in domains like computer vision and speech recognition.  ...  In contrast, the coarse-grain approach is immediately available no matter the nature of the deep neural network.  ... 
doi:10.1145/2851141.2851158 dblp:conf/ppopp/Tallada16 fatcat:ipabmp2f6revhfly6agikqkt74

A Survey of Convolutional Neural Networks on Edge with Reconfigurable Computing

Mário P. Véstias
2019 Algorithms  
The convolutional neural network (CNN) is one of the most used deep learning models for image detection and classification, due to its high accuracy when compared to other machine learning algorithms.  ...  CNNs achieve better results at the cost of higher computing and memory requirements. Inference of convolutional neural networks is therefore usually done in centralized high-performance platforms.  ...  Eyeriss [54] is a coarse-grain reconfigurable device that accelerates convolutional neural networks.  ... 
doi:10.3390/a12080154 fatcat:jbdak7eisbcjtj6ba5hlpvnq5y

Author Index

2020 2020 IEEE 33rd International System-on-Chip Conference (SOCC)  
Frequency Low Noise Amplifier for Low-Power RF Receivers Exploring the Scalability of OpenCL Coarse Grained Parallelism on Cloud FPGAs Efficient Metal Inter-Layer via Utilization Strategies for Three-Dimensional  ...  TR4.3 213 Exploring the Scalability of OpenCL Coarse Grained Parallelism on Cloud FPGAs Patooghy, Ahmad TP2.2 135 Mist-Scan: A Secure Scan Chain in Cryptographic Chips to Resist Scan-Based  ... 
doi:10.1109/socc49529.2020.9524726 fatcat:qluzc5nlwbbyrf7iy5d4pnsrhy

Selective and compressive sensing for energy-efficient implantable neural decoding

Aosen Wang, Chen Song, Xiaowei Xu, Feng Lin, Zhanpeng Jin, Wenyao Xu
2015 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)  
The screening module completes the low-effort classification task in the frontend and transmits the compressed data of high-effort task to remote server for fine-grained analysis.  ...  However, the overhead of signal reconstruction constrains the compression in sensor node and analysis in remote server.  ...  Fig. 1 . 1 The block diagram of the selective CS architecture for wireless implantable neural decoding. Fig. 2 . 2 The framework of deep belief networks.  ... 
doi:10.1109/biocas.2015.7348375 dblp:conf/biocas/WangS0LJX15 fatcat:7ap4a24fyzbpjmohtis4bhkg24

Context-modulation of hippocampal dynamics and deep convolutional networks [article]

James B. Aimone, William M. Severa
2017 arXiv   pre-print
We implement this concept in a deep artificial neural network by enabling a context-sensitive bias. The motivation for this is to improve performance of a size-constrained network.  ...  Complex architectures of biological neural circuits, such as parallel processing pathways, has been behaviorally implicated in many cognitive studies.  ...  Department of Energy's National Nuclear Security Administration under contract de-na0003525.  ... 
arXiv:1711.09876v1 fatcat:gaa5ey6qqfgndfai7x6gvo7ote

2021 Index IEEE Transactions on Parallel and Distributed Systems Vol. 32

2022 IEEE Transactions on Parallel and Distributed Systems  
., +, TPDS July 2021 1765-1776 Network routing Coarse-Grained Parallel Routing With Recursive Partitioning for FPGAs.  ...  ., +, TPDS July 2021 1802-1814 Coarse-Grained Parallel Routing With Recursive Partitioning for FPGAs. Efficient Methods for Mapping Neural Machine Translator on FPGAs.  ... 
doi:10.1109/tpds.2021.3107121 fatcat:e7bh2xssazdrjcpgn64mqh4hb4

Coarse-grained spectral projection (CGSP): a deep learning-assisted approach to quantum unitary dynamics [article]

Pinchen Xie, Weinan E
2020 arXiv   pre-print
We propose the coarse-grained spectral projection method (CGSP), a deep learning-assisted approach for tackling quantum unitary dynamic problems with an emphasis on quench dynamics.  ...  We show CGSP can extract spectral components of many-body quantum states systematically with sophisticated neural network quantum ansatz.  ...  This is done through a coarse-grained representation of the spectral projection with deep learning, a procedure we dubbed coarse-grained spectral projection (CGSP).  ... 
arXiv:2007.09788v2 fatcat:smtn7glnlve67feyqmqcll5jna

Balanced Sparsity for Efficient DNN Inference on GPU [article]

Zhuliang Yao, Shijie Cao, Wencong Xiao, Chen Zhang, Lanshun Nie
2018 arXiv   pre-print
In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage cost. However, it requires the customization of hardwares to speed up practical inference.  ...  Our approach adapts to high parallelism property of GPU, showing incredible potential for sparsity in the widely deployment of deep learning services.  ...  Shijie Cao was partly supported by National Nature Science Foundation of China (No.61772159).  ... 
arXiv:1811.00206v4 fatcat:3yptunrdnzchlepiikqwszhizu

Classifying Object Manipulation Actions based on Grasp-types and Motion-Constraints [article]

Kartik Gupta, Darius Burschka, Arnav Bhavsar
2018 arXiv   pre-print
In this work, we address a challenging problem of fine-grained and coarse-grained recognition of object manipulation actions.  ...  involving information of grasp and motion-constraints, c) Fine-grained and Coarse-grained object manipulation action recognition based on fine-grained as well as coarse-grained grasp type information,  ...  forest 0.7694 0.7972 Multi-class neural networks 0.8055 0.8015 Locally Deep SVM (Binary) 0.8028 0.7982 SVM (Binary) 0.7694 0.7953 Neural Networks (Binary) 0.8055 0.7977 Ensemble 0.8000  ... 
arXiv:1806.07574v1 fatcat:4vtq63rgxbbkjlr5zbalw2oufe

Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification [article]

Xiu-Shen Wei, Chen-Lin Zhang, Lingqiao Liu, Chunhua Shen, Jianxin Wu
2018 arXiv   pre-print
Specifically, humans always firstly determine one vehicle's coarse-grained category, i.e., the car model/type.  ...  Then, under the branch of the predicted car model/type, they are going to identify specific vehicles by relying on subtle visual cues, e.g., customized paintings and windshield stickers, at the fine-grained  ...  Deep neural networks Deep convolutional neural networks (DCNNs) try to model the high-level abstractions of the visual data by using architectures composed of multiple non-linear transformations.  ... 
arXiv:1812.04239v1 fatcat:suophtgl7vexxhnnhmsw6befeu

A Graph-Related High-Order Neural Network Architecture via Feature Aggregation Enhancement for Identification Application of Diseases and Pests

Jianlei Kong, Chengcai Yang, Yang Xiao, Sen Lin, Kai Ma, Qingzhen Zhu, Xin Ning
2022 Computational Intelligence and Neuroscience  
Toward this end, this paper proposes an effective graph-related high-order network with feature aggregation enhancement (GHA-Net) to handle the fine-grained image recognition of plant pests and diseases  ...  Disease and pest recognition is typically a fine-grained visual classification problem, which is easy to confuse the traditional coarse-grained methods due to the external similarity between different  ...  Coarse-Grained Deep Learning Recognition Approaches.  ... 
doi:10.1155/2022/4391491 pmid:35665281 pmcid:PMC9162821 fatcat:2344c2ov3jb6pjf6jcobwk5fli

A Multiple-layer Representation Learning Model for Network-Based Attack Detection

Xueqin Zhang, Jiahao Chen, Yue Zhou, Liangxiu Han, Jiajun Lin
2019 IEEE Access  
INDEX TERMS Network intrusion detection, convolutional neural networks, deep random forests, representation learning. This work is licensed under a Creative Commons Attribution 4.0 License.  ...  To address these issues, this work has proposed a multiple-layer representation learning model for accurate end-to-end network intrusion detection by combining deep convolutional neural networks (CNN)  ...  The former one is inspired by the representation learning in deep neural networks, which mostly relies on the layer-by-layer processing of raw features.  ... 
doi:10.1109/access.2019.2927465 fatcat:2pzvs4xvanh2dfnzfmptohtapu

Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization [article]

Ruyi Ji, Longyin Wen, Libo Zhang, Dawei Du, Yanjun Wu, Chen Zhao, Xianglong Liu, Feiyue Huang
2020 arXiv   pre-print
The deep convolutional operations learn to capture the representations of objects, and the tree structure characterizes the coarse-to-fine hierarchical feature learning process.  ...  An attention convolutional binary neural tree architecture is presented to address those problems for weakly supervised FGVC.  ...  Frosst and Hinton [11] develop a deep neural decision tree model to understand decision mechanism for particular test case in a learned network. Tanno et al.  ... 
arXiv:1909.11378v2 fatcat:fxvepmlnwvejfdf5m4coiksfsu

Minimizing Area and Energy of Deep Learning Hardware Design Using Collective Low Precision and Structured Compression [article]

Shihui Yin, Gaurav Srivastava, Shreyas K. Venkataramanaiah, Chaitali Chakrabarti, Visar Berisha, Jae-sun Seo
2018 arXiv   pre-print
Deep learning algorithms have shown tremendous success in many recognition tasks; however, these algorithms typically include a deep neural network (DNN) structure and a large number of parameters, which  ...  However, combining various sparsity structures with binarized or very-low-precision (2-3 bit) neural networks have not been comprehensively explored.  ...  INTRODUCTION Deep neural networks (DNNs) have seen great success in many cognitive applications such as image classification [1] [2] and speech recognition [3] .  ... 
arXiv:1804.07370v1 fatcat:hirsopx7czbexffugk6a3iixmm

ACEnet: Anatomical Context-Encoding Network for Neuroanatomy Segmentation [article]

Yuemeng Li, Hongming Li, Yong Fan
2021 arXiv   pre-print
In order to overcome this limitation, we develop an Anatomical Context-Encoding Network (ACEnet) to incorporate 3D spatial and anatomical contexts in 2D convolutional neural networks (CNNs) for efficient  ...  Since 3D deep learning models suffer from high computational cost, 2D deep learning methods are favored for their computational efficiency.  ...  To achieve fast and accurate segmentation of fine-grained brain structures from MR scans, we develop a deep neural network for segmenting 2D slices of MR scans by integrating 3D spatial and anatomical  ... 
arXiv:2002.05773v3 fatcat:7xqhiedtgjbjhkiku3ge6zpava
« Previous Showing results 1 — 15 out of 7,612 results