Proceedings of the 15th ACM International Conference on Computing Frontiers最新文献

筛选

英文中文

QUENN: QUantization engine for low-power neural networks 用于低功耗神经网络的量化引擎

Proceedings of the 15th ACM International Conference on Computing Frontiers Pub Date : 2018-05-08 DOI: 10.1145/3203217.3203282

Miguel de Prado, Maurizio Denna, L. Benini, Nuria Pazos

{"title":"QUENN: QUantization engine for low-power neural networks","authors":"Miguel de Prado, Maurizio Denna, L. Benini, Nuria Pazos","doi":"10.1145/3203217.3203282","DOIUrl":"https://doi.org/10.1145/3203217.3203282","url":null,"abstract":"Deep Learning is moving to edge devices, ushering in a new age of distributed Artificial Intelligence (AI). The high demand of computational resources required by deep neural networks may be alleviated by approximate computing techniques, and most notably reduced-precision arithmetic with coarsely quantized numerical representations. In this context, Bonseyes comes in as an initiative to enable stakeholders to bring AI to low-power and autonomous environments such as: Automotive, Medical Healthcare and Consumer Electronics. To achieve this, we introduce LPDNN, a framework for optimized deployment of Deep Neural Networks on heterogeneous embedded devices. In this work, we detail the quantization engine that is integrated in LPDNN. The engine depends on a fine-grained workflow which enables a Neural Network Design Exploration and a sensitivity analysis of each layer for quantization. We demonstrate the engine with a case study on Alexnet and VGG16 for three different techniques for direct quantization: standard fixed-point, dynamic fixed-point and k-means clustering, and demonstrate the potential of the latter. We argue that using a Gaussian quantizer with k-means clustering can achieve better performance than linear quantizers. Without retraining, we achieve over 55.64% saving for weights' storage and 69.17% for run-time memory accesses with less than 1% drop in top5 accuracy in Imagenet.","PeriodicalId":127096,"journal":{"name":"Proceedings of the 15th ACM International Conference on Computing Frontiers","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128785229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

Proceedings of the 15th ACM International Conference on Computing Frontiers 第15届ACM计算前沿国际会议论文集

Proceedings of the 15th ACM International Conference on Computing Frontiers Pub Date : 1900-01-01 DOI: 10.1145/3203217

引用次数: 1

首页上一页