Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity

Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity

碩士 === 國立交通大學 === 電子研究所 === 105

Bibliographic Details
Main Authors: Lin, Chien-Yu, 林建宇
Other Authors: Lai, Bo-Cheng
Format: Others
Language:en_US
Published: 2017
Online Access:http://ndltd.ncl.edu.tw/handle/6aq7yc
id ndltd-TW-105NCTU5428148
record_format oai_dc
spelling ndltd-TW-105NCTU54281482019-05-16T00:08:09Z http://ndltd.ncl.edu.tw/handle/6aq7yc Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity Merlin: 一個有效利用神經元及權重稀疏性的類神經網路加速器設計 Lin, Chien-Yu 林建宇 碩士 國立交通大學 電子研究所 105 Lai, Bo-Cheng 賴伯承 2017 學位論文 ; thesis 48 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立交通大學 === 電子研究所 === 105
author2 Lai, Bo-Cheng
author_facet Lai, Bo-Cheng
Lin, Chien-Yu
林建宇
author Lin, Chien-Yu
林建宇
spellingShingle Lin, Chien-Yu
林建宇
Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity
author_sort Lin, Chien-Yu
title Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity
title_short Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity
title_full Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity
title_fullStr Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity
title_full_unstemmed Merlin: A Sparse Neural Network Accelerator Utilizing Both Neuron and Weight Sparsity
title_sort merlin: a sparse neural network accelerator utilizing both neuron and weight sparsity
publishDate 2017
url http://ndltd.ncl.edu.tw/handle/6aq7yc
work_keys_str_mv AT linchienyu merlinasparseneuralnetworkacceleratorutilizingbothneuronandweightsparsity
AT línjiànyǔ merlinasparseneuralnetworkacceleratorutilizingbothneuronandweightsparsity
AT linchienyu merlinyīgèyǒuxiàolìyòngshénjīngyuánjíquánzhòngxīshūxìngdelèishénjīngwǎnglùjiāsùqìshèjì
AT línjiànyǔ merlinyīgèyǒuxiàolìyòngshénjīngyuánjíquánzhòngxīshūxìngdelèishénjīngwǎnglùjiāsùqìshèjì
_version_ 1719160690032246784

Similar Items