A learning rule for asynchronous perceptrons with feedback in a combinatorial environment

By L. B. Almeida. 1990

How researchers see this paper

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

In Reinforcement Learning

Citations in the corpus

Gated Graph Sequence Neural Networks (2015, methodology): “Learning is done via the Almeida-Pineda algorithm (Almeida, 1990; Pineda, 1987), which works by running the propagation to convergence, and then computing gradients based upon the converged solution.”
The Graph Neural Network Model (2009, neutral): “6 On the other hand, in our case, a more efficient approach is possible, based on the Almeida–Pineda algorithm [58], [59].”
Deep learning in neural networks: An overview (2014, neutral): “, 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, 1989a, 1989b), also for equilibrium RNNs (Almeida, 1987; Pineda,”
On the Binding Problem in Artificial Neural Networks (2020, background): “Attractor states were also found to occur naturally in RNNs, especially when using symmetric recurrent weights (Almeida, 1987; Pineda, 1987).”
Graph Normalizing Flows (2019, background): “A recent approach for memory saving based on recurrent backpropagation (RBP) [1, 20, 18] requires running message passing to convergence, followed by the approximate, iterative inversion of a large matrix.”
Incremental Few-Shot Learning with Attention Attractor Networks (2018, methodology): “We also show how this regularizer can be optimized, using recurrent back-propagation (Liao et al., 2018; Almeida, 1987; Pineda, 1987) we show empirically that our proposed method can produce state-of-the-art results in incremental few-shot learning on the challenging mini -ImageNet (Vinyals et al.,…”
A Comprehensive Survey on Graph Neural Networks (2019, methodology): “rinks the distance between two points after mapping. In case of f( ) is a neural network, a penalty term has to be imposed on the Jacobian matrix of parameters. GNNs used the Almeida-Pineda algorithm [77], [78] to train its model. The core idea is to run the propagation process to reach ﬁxed points ”
Residual Flows for Invertible Generative Modeling (2019, neutral): “On the other hand, our approach shares some similarities with Recurrent Backpropagation (Almeida, 1987; Pineda, 1987; Liao et al., 2018), since both approaches leverage convergent dynamics to modify the derivatives.”
Deep Equilibrium Models (2019, background): “Let x 1: T ∈ R T × p be the input sequence, and θ [1] , θ [2] the sets of parameters for stable transformations f θ [1] : R r × R p → R r and v θ [2] : R d × R r → R d , respectively. where Then there exists Γ Θ : R d + r × R p → R d + r , Θ = θ [1] ∪ θ [2] , s.t.”
On Training Recurrent Networks with Truncated Backpropagation Through time in Speech Recognition (2018, background): “There are many approaches to training recurrent networks [22, 23], and the most successful one by far is backpropagation through time [13].”
Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning (2001, methodology): “additional evidence for the idea that interactivity impair s generalization, networks using the Almeida-Pineda (AP) fixed-point recurrent backpropagation algorithm (Alm eida, 1987; Pineda, 1987b, 1987a, 1988) were also run. This algorithm is a mathematically direct extensi o of feedforward error bac”
A Proposal on Machine Learning via Dynamical Systems (2017, background): “We note that continuous dynamical systems approach was mentioned in [6–8].”
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures (2018, background): “Researchers have long sought biologically plausible and empirically powerful learning algorithms that avoid these flaws [2, 30, 31, 1, 26, 39, 14, 16, 12, 5, 23].”
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks (1989, background): “memory networks, have been proposed by Hop eld (1982), Lapedes and Farber (1986), Almeida (1987), Pineda (1988), and Rohwer and Forrest (1987). Other researchers have focused on learning algorithms for more general networks that use recurrent connections to deal with time-varying input and/or output”
Experimental Analysis of the Real-time Recurrent Learning Algorithm (1989, background): “Almeida (1987), Pineda (1988) and Rohwer & Forrest (1987) have all derived various versions of this algorithm, and Almeida has made the useful observation that the corresponding backpropagation computation, itself involving a settling operation, necessarily converges stably whenever the forward comp”
Graph neural networks in particle physics (2020, methodology): “The first GNNs [32, 33] were developed and applied for network analysis, especially on internet data, and were trained not with the back-propagation algorithm, but with fixed point iteration via the Almeida–Pineda algorithm [34, 35].”
Multiscale Deep Equilibrium Models (2020, background): “Pineda [43] and Almeida [2] studied implicit differentiation techniques for training recurrent dynamics, also known as recurrent back-propagation (RBP) [37].”
How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation (2014, background): “There are also iterative forms of target propagation such as in the Almeida-Pineda recurrent networks (Almeida, 1987; Pineda, 1987) and in the generalized recirculation algorithm (O’Reilly, 1996).”