ePoster · Machine Learning
Co-evolved structural and temporal network heterogeneity
Stefan Iacob, Nishant Joshi, Joni Dambre, Fleur Zeldenrust · Bernstein Conference 2024
Contrary to typical artificial neural network (ANN) design, biological neurons are not identical. Neurons differ substantially in their physiological properties. Heterogeneity has been hypothesized to increase the dimensionality of the neural dynamics, which improves the encoding properties of a network [1], promotes robustness and stability [2], and maximizes information flow in large networks [3]. We aim to show the functional effect of heterogeneity in rate-based recurrent neural networks. To vary the degree of heterogeneity, we introduce neuron types, with each neuron type having its own