Recurrent neural networks for source code generation
Source code generation is a highly challenging research area. With the successes recurrent neural networks (RNNs) had in natural language processing, it is only natural that researchers try to apply them to the task of code generation as well.
At the seminar, we will discuss applications of RNNs for generating AST trees.
Speaker: Yaroslav Sokolov.
Presentation language: Russian.
Date and time: April 3rd, 20:00-21:30.
Location: Times, room 204.
Videos from previous seminars are available at http://bit.ly/MLJBSeminars
- About seminars
22 May 2019An Empirical Study on Quality of Android Applications written in Kotlin language
15 May 2019Who Should Make Decision on this Pull Request? Analyzing Time-Decaying Relationships and File Similarities for Integrator Prediction
8 May 2019Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
24 April 2019Siamese: scalable and incremental code clone search via multiple code representations
17 April 2019An Approach and Benchmark to Detect Behavioral Changes of Commits in Continuous Integration