Abstract
Spiking Neural Networks constitute the most promising approach to develop realistic Artificial Neural Networks (ANNs). Unlike traditional firing rate-based paradigms, information coding in spiking models is based on the precise timing of individual spikes. It has been demonstrated that spiking ANNs can be successfully and efficiently applied to multiple realistic problems solvable with traditional strategies (e.g., data classification or pattern recognition). In recent years, major breakthroughs in neuroscience research have discovered new relevant computational principles in different living neural systems. Could ANNs benefit from some of these recent findings providing novel elements of inspiration? This is an intriguing question for the research community and the development of spiking ANNs including novel bio-inspired information coding and processing strategies is gaining attention. From this perspective, in this work, we adapt the core concepts of the recently proposed Signature Neural Network paradigm—i.e., neural signatures to identify each unit in the network, local information contextualization during the processing, and multicoding strategies for information propagation regarding the origin and the content of the data—to be employed in a spiking neural network. To the best of our knowledge, none of these mechanisms have been used yet in the context of ANNs of spiking neurons. This paper provides a proof-of-concept for their applicability in such networks. Computer simulations show that a simple network model like the discussed here exhibits complex self-organizing properties. The combination of multiple simultaneous encoding schemes allows the network to generate coexisting spatio-temporal patterns of activity encoding information in different spatio-temporal spaces. As a function of the network and/or intra-unit parameters shaping the corresponding encoding modality, different forms of competition among the evoked patterns can emerge even in the absence of inhibitory connections. These parameters also modulate the memory capabilities of the network. The dynamical modes observed in the different informational dimensions in a given moment are independent and they only depend on the parameters shaping the information processing in this dimension. In view of these results, we argue that plasticity mechanisms inside individual cells and multicoding strategies can provide additional computational properties to spiking neural networks, which could enhance their capacity and performance in a wide variety of real-world tasks.
Highlights
Biological neural circuits are powerful computational systems that efficiently process a great amount of data in real time with extensive plasticity capabilities
Temporal coding emerges as a strategy commonly used by neural systems, emphasizing that, unlike the firing rate paradigm, neural information may be carried by precise individual spike timings
I.e., networks not receiving external input, the level of bursting activity depends on the transit probability of the internal state (p), the firing threshold (TH), and the duration of the refactory period (RP)
Summary
Biological neural circuits are powerful computational systems that efficiently process a great amount of data in real time with extensive plasticity capabilities This makes the nervous system a source of inspiration when designing engineered tools. Experimental evidence indicates that living neural systems use many different information coding strategies (Rabinovich et al, 2006b; Middleton et al, 2011), which greatly enhances their processing capacity as compared to the classical view In this scenario, temporal coding emerges as a strategy commonly used by neural systems, emphasizing that, unlike (or in addition to) the firing rate paradigm, neural information may be carried by precise individual spike timings (e.g., see Mainen and Sejnowski, 1995; Lestienne, 1996; Diesmann et al, 1999; Reinagel and Reid, 2002)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have