79 citations · 148 across the 10 of their papers we have counts for
10 papers
Memorisation and forgetting in a learning Hopfield neural network: bifurcation mechanisms, attractors and basins
Adam E. Essex, Natalia B. Janson, Rachel A. Norris +1
Despite explosive expansion of artificial intelligence based on artificial neural networks (ANNs), these are employed as "black boxes'', as it is unclear how, during learning, they…
Optimization with delay-induced bifurcations
Natalia B. Janson, Christopher J. Marsden
Optimization is finding the best solution, which mathematically amounts to locating the global minimum of some cost function. Optimization is traditionally automated with digital o…
Delay-induced homoclinic bifurcations in modified gradient bistable systems and their relevance to optimisation
Natalia B. Janson, Christopher J. Marsden
Nonlinear dynamical systems with time delay are abundant in applications, but are notoriously difficult to analyse and predict because delay-induced effects strongly depend on the…
Asymptotic behaviour of dynamical systems with plastic self-organising vector fields
N. B. Janson, P. E. Kloeden
In [Janson & Marsden 2017] a dynamical system with a plastic self-organising velocity vector field was introduced, which was inspired by the architectural plasticity of the brain a…
Conceptual model of a cognitive system: dynamical system with plastic self-organizing velocity field
Natalia B. Janson, Christopher J. Marsden
Spontaneously evolving living systems can be modelled as continuous-time dynamical systems (DSs), whose evolution rules are determined by their velocity vector fields. We point out…
Self-shaping dynamical systems and learning
Natalia B. Janson, Christopher J. Marsden
We associate learning and adaptation in living systems with the shaping of the velocity vector field in the respective dynamical systems in response to external, generally random,…