Eylem Seç
Design and Implementation of a Domain Specific Language for Deep Learning
Başlık:
Design and Implementation of a Domain Specific Language for Deep Learning
Yazar:
Huang, Xiao Bing, author. (orcid)0000-0002-1198-9526
ISBN:
9780355988000
Yazar Ek Girişi:
Fiziksel Tanımlama:
1 electronic resource (135 pages)
Genel Not:
Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Advisors: Tian Zhao Committee members: Yu Cao; Susan McRoy; Xiangming Mu; Ethan Munson.
Özet:
Deep Learning (DL) has found great success in well-diversified areas such as machine vision, speech recognition, big data analysis, and multimedia understanding recently. However, the existing state-of-the-art DL frameworks, e.g. Caffe2, Theano, TensorFlow, MxNet, Torch7, and CNTK, are programming libraries with fixed user interfaces, internal representations, and execution environments. Modifying the code of DL layers or data structure is very challenging without in-depth understanding of the underlying implementation. The optimization of the code and execution in these tools is often limited and relies on the specific DL computation graph manipulation and scheduling that lack systematic and universal strategies. Furthermore, most of these tools demand many dependencies beside the tool itself and require to be built to some specific platforms for DL training or inference.
This dissertation presents DeepDSL, a domain specific language (DSL) embedded in Scala, that compiles DL networks encoded with DeepDSL to efficient, compact, and portable Java source programs for DL training and inference. DeepDSL represents DL networks as abstract tensor functions, performs symbolic gradient derivations to generate the Intermediate Representation (IR), optimizes the IR expressions, and compiles the optimized IR expressions to cross-platform Java code that is easily modifiable and debuggable. Also, the code directly runs on GPU without additional dependencies except a small set of JNI (Java Native Interface) wrappers for invoking the underneath GPU libraries. Moreover, DeepDSL provides static analysis for memory consumption and error detection.
DeepDSL has been evaluated with many current state-of-the-art DL networks (e.g. Alexnet, GoogleNet, VGG, Overfeat, and Deep Residual Network). While the DSL code is highly compact with less than 100 lines for each of the network, the Java source code generated by the DeepDSL compiler is highly efficient. Our experiments show that the output java source has very competitive runtime performance and memory efficiency compared to the existing DL frameworks.
Notlar:
School code: 0263
Tüzel Kişi Ek Girişi:
Mevcut:*
Yer Numarası | Demirbaş Numarası | Shelf Location | Lokasyon / Statüsü / İade Tarihi |
---|---|---|---|
XX(680130.1) | 680130-1001 | Proquest E-Tez Koleksiyonu | Arıyor... |
On Order
Liste seç
Bunu varsayılan liste yap.
Öğeler başarıyla eklendi
Öğeler eklenirken hata oldu. Lütfen tekrar deneyiniz.
:
Select An Item
Data usage warning: You will receive one text message for each title you selected.
Standard text messaging rates apply.