GRU: optimization of NPI performance

Currently, artificial intelligence is being used in automatic programming by producing snippets of code. NPI (neural programmer-interpreter) is the most used technology that uses machine learning to implement automatic programming. This paper is aimed to improve the performance of traditional NPI an...

Full description

Saved in:
Bibliographic Details
Published inThe Journal of supercomputing Vol. 76; no. 5; pp. 3542 - 3554
Main Authors Liu, Wei, Wang, Quan, Zhu, Yunlong, Chen, Hanning
Format Journal Article
LanguageEnglish
Published New York Springer US 01.05.2020
Springer Nature B.V
Subjects
Artificial intelligence
Compilers
Computer Science
Information flow
Interpreters
Machine learning
Optimization
Performance enhancement
Processor Architectures
Programming Languages
Automatic programming
Neural programmer-interpreter
GRU
Online AccessGet full text

Cover

More Information
Summary:Currently, artificial intelligence is being used in automatic programming by producing snippets of code. NPI (neural programmer-interpreter) is the most used technology that uses machine learning to implement automatic programming. This paper is aimed to improve the performance of traditional NPI and improve the speed of NPI training without loss of precision. To achieve this goal, we changed the core structure of NPI by adopting the GRU (gated recurrent unit) to replace LSTM (long short-term memory) in NPI. GRU has a control unit that regulates the flow of information within the hidden unit while without single memory unit. Numerical results have been presented to demonstrate the performance of the proposed methodology. That is, GRU-based NPI improved the performance of the original LSTM-based NPI by nearly 33% under the premise of ensuring equal accuracy.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-018-2634-9