Transient Chaos in BERT

I. Shimada and T. Nagashima, “A numerical approach to ergodic problem of dissipative dynamical systems,” Progress of theoretical physics , vol. 61, no. 6, pp. 1605–1616, 1979

1979

Earlier work this paper cites.

J. P. Crutchfield and K. Kaneko, “Are attractors relevant to turbulence?” Physical review letters , vol. 60, no. 26, p. 2715, 1988

1988

Earlier work this paper cites.

E. Ott, C. Grebogi, and J. A. Yorke, “Controlling chaos,” Physical review letters , vol. 64, no. 11, p. 1196, 1990

1990

Earlier work this paper cites.

J. B. Pollack, “The induction of dynamical recognizers,” in Connectionist Approaches to Language Learning . Springer, 1991, pp. 123–148

1991

Earlier work this paper cites.

K. Pyragas, “Continuous control of chaos by self-controlling feedback,” Physics letters A , vol. 170, no. 6, pp. 421–428, 1992

1992

Earlier work this paper cites.

T. Shinbrot, C. Grebogi, J. A. Yorke, and E. Ott, “Using small perturbations to control chaos,” nature , vol. 363, no. 6428, pp. 411–417, 1993

1993

Earlier work this paper cites.

Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE transactions on neural networks , vol. 5, no. 2, pp. 157–166, 1994

1994

Earlier work this paper cites.

J. L. Elman, “Language as a dynamical system,” Mind as motion: Explorations in the dynamics of cognition , pp. 195–223, 1995

1995

Earlier work this paper cites.

C. Moore, “Dynamical recognizers: Real-time language recognition by analog computers,” Theoretical Computer Science , vol. 201, no. 1-2, pp. 99–136, 1998

1998

Earlier work this paper cites.

N. Kataoka and K. Kaneko, “Natural language from function dynamics,” Biosystems , vol. 57, no. 1, pp. 1–11, 2000

2000

Earlier work this paper cites.

W. Maass, T. Natschläger, and H. Markram, “Real-time computing without stable states: A new framework for neural computation based on perturbations,” Neural computation , vol. 14, no. 11, pp. 2531–2560, 2002

2002

Earlier work this paper cites.

C. Kramsch, Language acquisition and language socialization: Ecological perspectives . Bloomsbury Publishing, 2003

2003

Earlier work this paper cites.

T. Ikegami and G. Morimoto, “Chaotic itinerancy in coupled dynamical recognizers,” Chaos: An Interdisciplinary Journal of Nonlinear Science , vol. 13, no. 3, pp. 1133–1147, 2003

2003

Cited alongside, same era.

H. Jaeger and H. Haas, “Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication,” science , vol. 304, no. 5667, pp. 78–80, 2004

2004

Cited alongside, same era.

W. G. Mitchener and M. A. Nowak, “Chaos and language,” Proceedings of the Royal Society of London. Series B: Biological Sciences , vol. 271, no. 1540, pp. 701–704, 2004

2004

Cited alongside, same era.

S. Ishihara and K. Kaneko, “Magic number 7 ± \pm 2 in networks of threshold dynamics,” Physical review letters , vol. 94, no. 5, p. 058102, 2005

2005

Cited alongside, same era.

A. Wang, A. Singh, J. Michael, F. Hill, O. Levy, and S. R. Bowman, “Glue: A multi-task benchmark and analysis platform for natural language understanding,” arXiv preprint arXiv:1804.07461 , 2018

Original

2018

Later among the works it cites.

J. Zhou, G. Cui, Z. Zhang, C. Yang, Z. Liu, L. Wang, C. Li, and M. Sun, “Graph neural networks: A review of methods and applications,” arXiv preprint arXiv:1812.08434 , 2018

Original

2018

Later among the works it cites.

Q. Li, Z. Han, and X.-M. Wu, “Deeper insights into graph convolutional networks for semi-supervised learning,” in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 32, no. 1, 2018

2018

Later among the works it cites.

V. Goudar and D. V. Buonomano, “Encoding sensory and motor patterns as time-invariant trajectories in recurrent neural networks,” Elife , vol. 7, p. e31134, 2018

2018

Later among the works it cites.