Online text prediction with recurrent neural networks

Neural Processing Letters

Volumn 14, Issue 2, 2001, Pages 127-140

  Pérez Ortiz, Juan Antonio ^a   Calera Rubio, Jorge ^a   Forcada, Mikel L ^a  

^a UNIVERSITY OF ALICANTE   (Spain)

Author keywords

Arithmetic coding; Online nonlinear prediction; Recurrent neural networks; Text compression

Indexed keywords

DATA COMPRESSION; DISCRETE TIME CONTROL SYSTEMS; ENCODING (SYMBOLS); ONLINE SYSTEMS; PROBABILITY;

ARITHMETIC CODING;

RECURRENT NEURAL NETWORKS;

EID: 0035482117     PISSN: 13704621     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1012491324276     Document Type: Article

References (22)

1. Learning long-term dependencies with gradient descent is difficult
2. Stable-encoding of finite-state machines in discrete-time recurrent neural nets with sigmoid units
3. Finite state automata and simple recurrent networks
4. Finding structure in time
5. Long short-term memory
6. Increased rates of convergence through learning rate adaptation
7. Text compression via alphabet re-representation
8. Fast text compression with neural networks
9. Identification and control of dynamical systems using neural networks
10. Arithmetic coding + statistical modeling = data compression
11. Data compression with the Burrows-Wheeler transform
12. Decoupled extended Kalman filter training of feedforward layered networks
13. A recurrent error propagation speech recognition system
14. Learning representations by back-propagating errors
15. Sequential neural text compression
16. A learning algorithm for continually training recurrent neural networks
17. A universal algorithm for sequential data compression