Related Experiment Videos
A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time
Benoît Siri1, Hugues Berry, Bruno Cessac
1Team Alchemy, INRIA, Parc Club Orsay Université, Orsay Cedex, France. benoit.siri@gmail.com
Abstract:
We present a mathematical analysis of the effects of Hebbian learning in random recurrent neural networks, with a generic Hebbian learning rule, including passive forgetting and different timescales, for neuronal activity and learning dynamics. Previous numerical work has reported that Hebbian learning drives the system from chaos to a steady state through a sequence of bifurcations. Here, we interpret these results mathematically and show that these effects, involving a complex coupling between neuronal dynamics and synaptic graph structure, can be analyzed using Jacobian matrices, which introduce both a structural and a dynamical point of view on neural network evolution. Furthermore, we show that sensitivity to a learned pattern is maximal when the largest Lyapunov exponent is close to 0. We discuss how neural networks may take advantage of this regime of high functional interest.
Related Concept Videos
Long-term Potentiation
Hebbian LTP
LTP can occur when presynaptic neurons...
Long-term Potentiation
Current Growth And Decay In RL Circuits
Woodward–Hoffmann Selection Rules and Microscopic Reversibility
Neural Circuits
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
BIBO stability of continuous and discrete -time systems
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system.