Fixed-weight networks can learn

By N. Cotter, Peter R. Conwell. 1990

How researchers see this paper

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

Meta-SGD: Learning to Learn Quickly for Few Shot Learning (2017, background): “Early studies show that recurrent neural networks (RNN) can model adaptive optimization algorithms [5, 26].”
Learning to reinforcement learn (2016, methodology): “Indeed, after an initial training period, the network can improve its performance on new tasks even if the weights are held constant (see also Cotter and Conwell, 1990; Prokhorov et al., 2002; Younger et al., 1999).”
A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification (1998, background): “Further, the work of Cotter and Conwell [ 7 ] suggests that time-lagged fixed-weight recurrent networks can produce behavior that would usually be called adaptive.”
Learning to Learn Using Gradient Descent (2001, background): “The capability of recurrent networks to execute the subordinate system was proved and demonstrated in [3,19].”
Fixed-weight on-line learning (1999, background): “HIS work builds on a series of introductory papers where we first discussed learning in fixed-weight networks [ 1 ]‐[4].”
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, background): “This approach has been well-studied in a supervised learning context [66, 31].”