Reservoir computing is a powerful computational framework that is particularly successful in time-series prediction tasks. It utilises a brain-inspired recurrent neural network and allows biologically plausible learning without backpropagation. Reservoir computing has relied extensively on the self-organizing properties of biological spiking neural networks. We examine the ability of a rate-based network of neural oscillators to take advantage of the self-organizing properties of synaptic plasticity. We show that such models can solve complex tasks and benefit from synaptic plasticity, which increases their performance and robustness. Our results further motivate the study of self-organizing biologically inspired computational models that do not exclusively rely on end-to-end training.

It has long been hypothesized that operating close to the critical state is beneficial for natural and artificial systems. We test this hypothesis by evolving foraging agents controlled by neural networks that can change the system's dynamical regime throughout evolution. Surprisingly, we find that all populations, regardless of their initial regime, evolve to be subcritical in simple tasks and even strongly subcritical populations can reach comparable performance. We hypothesize that the moderately subcritical regime combines the benefits of generalizability and adaptability brought by closeness to criticality with the stability of the dynamics characteristic for subcritical systems. By a resilience analysis, we find that initially critical agents maintain their fitness level even under environmental changes and degrade slowly with increasing perturbation strength. On the other hand, subcritical agents originally evolved to the same fitness, were often rendered utterly inadequate and degraded faster. We conclude that although the subcritical regime is preferable for a simple task, the optimal deviation from criticality depends on the task difficulty: for harder tasks, agents evolve closer to criticality. Furthermore, subcritical populations cannot find the path to decrease their distance to criticality. In summary, our study suggests that initializing models near criticality is important to find an optimal and flexible solution.