Time Warping Invariant Neural Networks

How researchers see this paper

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

Deep learning in neural networks: An overview (2014, background): “, 1995, 1996), certain hierarchical RNNs (Hihi and Bengio, 1996), RL economies in RNNs with WTA units and local learning rules (Schmidhuber, 1989b), and other methods (e.g., Ring, 1993, 1994; Plate, 1993; de Vries and Principe, 1991; Sun et al., 1993a; Bengio et al., 1994).”
Bridging Long Time Lags by Weight Guessing and \Long Short Term Memory" (1996, background): “…tasks, though, are more di(cid:14)cult than the above benchmark problems: they cannot be solved at all in reasonable time by random search (we tried various architectures) nor any other recurrent net learning algorithm we are aware of, e.g., [25, 20, 7, 8, 33, 14, 21, 5, 15, 29, 1, 24, 26, 19].”
Long short-term memory in recurrent neural networks (2001, methodology): “This performan e is mu h better than that of previous approa hes, where the largest set was learned by the spe ially designed neural push-down automaton (Sun et al., 1993; Das et al., 1992): n2f1;::; 160g.”
Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies (2001, background): “’s alternative approach [26] updates the activation of a recurrent unit by adding the old activation and the (scaled) current net input.”