Login    Contact Us    Search

RISE Lab

REAL-TIME INTELLIGENT SECURE EXECUTION Navigation
  • Home
  • People
  • Projects
  • Publications
  • Sponsors
  • DARE
  • Academics
  • News
  • Events
  • RISE Camp
  • Blogs
  • Jenkins
  • Search
  • Home
  • People
  • Projects
  • Publications
  • Sponsors
  • DARE
  • Academics
  • News
  • Events
  • RISE Camp
  • Blogs
  • Jenkins
  • Search

DeepCode

Deep learning models have been sucessfully applied to various areas including computer vision, natural language processing, etc. Little work has been done in the context of program synthesis, code completion in particular. In this work, we provide benchmark results for code completion on the Abstract Syntax Tree(AST) of JavaScripts code collected from Github. We have show the basic LSTM variants could achive 79% top 1 accuracy and 85.6% top 5 accuracy which is comparable to the probablistic model using much domain knowledge. We further evaluate the speed at serving phase, each query takes 33ms running on 16 core CPU and 16ms with one K80 GPU.

Xin Wang

xinw@berkeley.edu

Joey Gonzalez

jegonzal@cs.berkeley.edu

Share
Tweet
Share


Accessibility · Nondiscrimination · Privacy

 
  • Home
  • People
  • Projects
  • Publications
  • Sponsors
  • DARE
  • Academics
  • News
  • Events
  • RISE Camp
  • Blogs
  • Jenkins


The UCBerkeley RISELab is an NSF Expedition Project.