【電腦科學】【2020.05】【含原始碼】基於GO語言的深度學習

本文為美國普渡大學（作者：Derek L. Stinson）的碩士論文，共66頁。

目前深度學習的研究主要集中在使用Python作為支援語言上。Go是一種新興的語言，它有許多優點，包括對併發的本地支援，在過去幾年中，它的採用率有所上升。然而，由於缺乏模型開發的支援庫和框架，這種語言並沒有被廣泛用於開發學習模型。在本論文中，利用Go進行神經網路模型的一般開發和卷積神經網路的研究。這項研究是基於一個稱為GoCuNets神經網路模型的Go-CUDA實現，然後將這個實現與GO-CPU深度學習實現進行比較，後者利用了Go內建的ConvNetGo併發性。對這兩種實現方式的比較表明，與ConvNetGo相比，使用GoCuNets時的效能顯著提高。

Current research in deep learning is primarily focused on using Python as a support language. Go, an emerging language, that has many benefits including native support for concurrency has seen a rise in adoption over the past few years. However, this language is not widely used to develop learning models due to the lack of supporting libraries and frameworks for model development. In this thesis, the use of Go for the development of neural network models in general and convolution neural networks is explored. The proposed study is based on a Go-CUDA implementation of neural network models called GoCuNets. This implementation is then compared to a Go-CPU deep learning implementation that takes advantage of Go’s built in concurrency called ConvNetGo. A comparison of these two implementations shows a significant performance gain when using GoCuNets compared to ConvNetGo.

1.   引言
   

2. 相關工作
3. 研究方法
4. 結果
5. 結論
   附錄A ConvNetGo
   附錄B GoCuNets
   附錄C GoCudnn

更多精彩文章請關注公眾號：