A learning algorithm for analog, fully recurrent neural networks

By Michael Gherrity. 1989

How researchers see this paper

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

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “See generalizations for sequenceprocessing recurrent NNs (e.g., Atiya & Parlos, 2000; Baldi, 1995; Gherrity, 1989; Kremer & Kolen, 2001; Pearlmutter, 1989, 1995; Robinson & Fallside, 1987; Rohwer, 1989; Schmidhuber, 1992a; Werbos, 1988;Williams, 1989;Williams & Peng, 1990;Williams & Zipser, 1988,…”
A local learning algorithm for dynamic feedforward and recurrent networks (1990, background): “Various algorithms for supervised learning in recurrent non-equilibrium networks with non-stationary inputs and outputs have been proposed (Robinson & Fallside, 1987; Williams & Zipser, 1988; Pearlmutter, 1988; Gherrity, 1989; Rohwer, 1989).”
Gradient-based learning algorithms for recurrent connectionist networks (1990, background): “…and Fallside (1987), Kuhn (1987), Bachrach(1988), Mozer (1988), and Williams and Zipser (1989a), and continuous-time versions have beenproposed by Gherrity (1989) and by Doya and Yoshizawa (1989).5.1 The AlgorithmFor each k 2 U , i 2 U , j 2 U [ I, and t0 t t1, we de nepkij(t) = @yk(t)@wij :…”
Making the World Di erentiable: On Using Self-Supervised Fully Recurrent Neural Networks for Dynamic Reinforcement Learning (1990, background): “Pearlmutter [18] and Gherrity [5] described continuous time versions of the method.”
An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories (1990, background): “Such information involving the distant past is also present in RTRL, albeit implicitly, and Gherrity (1989) has specifically addressed this issue by incorporating into his continuous-time version of RTRL an exponential decay on the contributions from past times.”
Gradient-based learning algorithms for recurrent networks and their computational complexity (1995, background): “Such information is also present in RTRL, albeit implicitly, and Gherrity (1989) has specifically addressed this issue by incorporating into his continuous-time version of RT'RL an exponential decay on the contributions from past times.”
Making the world differentiable: on using self supervised fully recurrent neural networks for dynamic reinforcement learning and planning in non-stationary environments (1990, background): “Pearlmutter [19] and Gherrity [5] described continuous time versions of the method.”
A Fixed Size Storage O(n3) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks (1992, methodology): “Following the argumentation in (Williams and Peng, 1990), continuous time versions of BPTT and RTRL (Pearlmutter, 1989) (Gherrity, 1989) can serve as a basis for a correspondingly eecient continuous time version of the algorithm presented here (by means of Euler discretization).”
Learning Algorithms for Networks with Internal and External Feedback (1990, background): “This approach has been pursued by (Robinson and Fallside, 1987), (Werbos, 1988), (Pearlmutter, 1989), (Rumelhart et al., 1986), (Williams and Zipser, 1989), (Gherrity, 1989) and others in the case where there is only internal feedback.”
Learning Unambiguous Reduced Sequence Descriptions (1991, background): “Since only unpredictable inputs convey new information, ignore all predictable inputs but let all unexpected inputs (plus information about the time step at which they occurred) become inputs to a higher-level network of the same kind (working on a slower, self-adjusting time scale).”