RAAM for infinite context-free languages

By O. Melnik, Simon D. Levy, Jordan B. Pollack. 2000

11 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Alan D. Blair
2. J. Urgen Schmidhuber
3. Stephan K. Chalup
4. Yonatan Belinkov
5. David R Ha
6. Alex Graves
7. Sergey Levine
8. Yoshua Bengio

In Computational Theory and Mathematics

1. J. Urgen Schmidhuber
2. Stephan K. Chalup
3. Alan D. Blair
4. David R Ha
5. Sergey Levine
6. Jeff Clune
7. Pierre-Yves Oudeyer
8. Tom Schaul

In Molecular Biology

1. Alan D. Blair
2. J. Urgen Schmidhuber
3. Stephan K. Chalup

Citations in the corpus

• Deep learning in neural networks: An overview (2014, methodology): “Compare an early survey (Hinton, 1989) and the somewhat related Recursive Auto-Associative Memory (RAAM) (Pollack, 1988, 1990; Melnik et al., 2000), originally used to encode linguistic structures, but later also as an unsupervised pre-processor to facilitate deep credit assignment for RL (Gisslen e”
• Incremental training of first order recurrent neural networks to predict a context-sensitive language (2003, background): “In two recent studies, Melnik, Levy, and Pollack (2000) evolved RAAM networks capable of expressing all strings of the a n b n language, while Gers and Schmidhuber (2001) trained long short-term memory networks to predict the a n b n c n language with substantial generalisation ability.”