Self-organization, scaling, and parallelism

The problem of learning in the absence of external intelligence is discussed in the context of a simple model. The model departs from the traditional gradient-descent based approaches to learning by operating at a highly susceptible “critical” state, with low activity and sparse connections between firing neurons. Quantitative studies in the context of two simple association tasks demonstrate that the elements of the model that are essential for self-organized learning are also essential for its scaling performance and parallelism