Synaptic Learning with Augmented Spikes
This work addresses a bottleneck in spiking neural networks for researchers in neuromorphic computing, offering a novel approach that is versatile and generalizable, though it appears incremental in advancing existing spike-based paradigms.
The paper tackles the problem of combining the accuracy of analog values with the time-processing capability of spikes in neural models by introducing augmented spikes with coefficients and latencies, resulting in effective methods for tasks like acoustic and visual pattern recognition with notable performance.
Traditional neuron models use analog values for information representation and computation, while all-or-nothing spikes are employed in the spiking ones. With a more brain-like processing paradigm, spiking neurons are more promising for improvements on efficiency and computational capability. They extend the computation of traditional neurons with an additional dimension of time carried by all-or-nothing spikes. Could one benefit from both the accuracy of analog values and the time-processing capability of spikes? In this paper, we introduce a concept of augmented spikes to carry complementary information with spike coefficients in addition to spike latencies. New augmented spiking neuron model and synaptic learning rules are proposed to process and learn patterns of augmented spikes. We provide systematic insight into the properties and characteristics of our methods, including classification of augmented spike patterns, learning capacity, construction of causality, feature detection, robustness and applicability to practical tasks such as acoustic and visual pattern recognition. The remarkable results highlight the effectiveness and potential merits of our methods. Importantly, our augmented approaches are versatile and can be easily generalized to other spike-based systems, contributing to a potential development for them including neuromorphic computing.