Continually Learning People Detection from DVS Data

This chapter provides a first analysis of how biologically plausible spiking neural networks (SNNs) equipped with spike-timing-dependent plasticity (STDP) can learn to detect people on the fly from non-independent and identically distributed (non-i.i.d.) streams of retina-inspired, event camera data. The system presented in this chapter works as follows. First, a short sequence of event data, capturing a walking human from a flying drone, is forwarded in its natural order to an SNN-STDP system, which also receives teacher spiking signals from the neural activity readout block. Then, when the end of the learning sequence is reached, the learned system is assessed on testing sequences. In addition, a new interpretation of anti-Hebbian plasticity is also presented as an over-fitting control mechanism and provides experimental demonstrations of our findings. This work contributes to the study of attention-based development and perception in bio-inspired systems.