Related Experiment Video
Updated: Aug 21, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
Inaccessibility in online learning of recurrent neural networks
Asaki Saito1, Makoto Taiji, Takashi Ikegami
1Future University-Hakodate, 116-2 Kameda Nakano-cho, Hakodate, Hokkaido 041-8655, Japan.
Abstract:
We apply nonlinear dynamical system techniques to recurrent neural networks. In particular, we numerically analyze the dynamical system characteristics of the online learning process. By introducing the notion of inaccessibility, we show that the learning process is well characterized by strong nonhyperbolicity and inaccessibility, which is a greater uncertainty than chaotic unpredictability. These results are clearly contrasted with a gradient descent dynamics, or ordinary chaos.
Related Concept Videos
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Introduction to Learning
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Associative Learning
Classical conditioning, also known...