【摘要】：2006年深度學習的提出為機器學習領域帶來新的革命,深度學習的成功不僅依賴于理論和模型上的突破,也離不開大數(shù)據(jù)環(huán)境下的海量訓練樣本以及不斷革新的先進計算技術(shù)。在GPU被應用于科學計算之前,神經(jīng)網(wǎng)絡特別是大型神經(jīng)網(wǎng)絡的訓練時間往往令人生畏。GPU特別適應于并行計算的特性給神經(jīng)網(wǎng)絡的訓練速度帶來數(shù)十倍的提升。開源的GPU計算框架也不斷地推陳出新,推動深度學習在各方面的應用,Caffe就是其中的一種。由于簡單易用、性能強大,Caffe框架受到了廣泛的認可。利用Caffe框架對印章類型進行識別,所采用的兩種模型都取得極好的實驗效果,對印章的自動識別提供新的參考。
[Abstract]:In 2006, the proposal of deep learning brought a new revolution to the field of machine learning. The success of deep learning not only depends on the breakthrough of theory and model, but also depends on the massive training samples and innovative advanced computing technology in big data environment. Before GPU was applied to scientific computing, the training time of neural network, especially large neural network, was often daunting. GPU is especially suitable for parallel computing, which brings dozens of times improvement to the training speed of neural network. Open source GPU computing framework is also constantly innovative, promoting in-depth learning in all aspects of the application, Caffe is one of them. Because of its simple and easy to use and powerful performance, Caffe framework has been widely recognized. The Caffe framework is used to identify the seal types, and the two models have achieved excellent experimental results, which provides a new reference for the automatic recognition of seals.
【作者單位】： 四川大學計算機學院;
【基金】：國家自然科學基金資助項目(61303015) 四川省科技計劃項目(No.2014GZ0005-5)
【分類號】：TP391.41

【參考文獻】

相關碩士學位論文 前1條

1 尚利峰;脈沖耦合神經(jīng)網(wǎng)絡在圖像處理中的應用[D];電子科技大學;2007年

【共引文獻】

相關碩士學位論文 前2條

1 陳龍斌;基于脈沖耦合神經(jīng)網(wǎng)絡的圖像分割與圖像融合研究[D];云南大學;2015年

2 胡芳;脈沖耦合神經(jīng)網(wǎng)絡在圖像分割和人臉檢測中的應用研究[D];云南大學;2011年

，

本文編號：2500433