1. Главная
  2. Ресурсы
  3. Библиотечный поиск
LSTM: A Search SpaceOdyssey Klaus GreffRupesh K. SrivastavaJan Koutník2016 год

LSTM: A Search Space Odyssey
статья из журнала

Полный текстСтраница публикацииПубликация в OpenAlex
Аннотация: Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful fANOVA framework. In total, we summarize the results of 5400 experimental runs ($\approx 15$ years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
Год издания: 2016
Авторы: Klaus Greff, Rupesh K. Srivastava, Jan Koutník, Bas R. Steunebrink, Jürgen Schmidhuber
Издательство: Institute of Electrical and Electronics Engineers
Источник: IEEE Transactions on Neural Networks and Learning Systems
Ключевые слова: Music and Audio Processing, Speech Recognition and Synthesis, Handwritten Text Recognition Techniques
Другие ссылки: IEEE Transactions on Neural Networks and Learning Systems (HTML)
arXiv (Cornell University) (PDF)
arXiv (Cornell University) (HTML)
arXiv (Cornell University) (PDF)
arXiv (Cornell University) (HTML)
PubMed (HTML)
DataCite API (HTML)