Spike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification task

Abstract

Spiking Neural Networks (SNNs), known for their potential to enable low energy consumption and computational cost, can bring significant advantages to the realm of embedded machine learning for edge applications. However, input coming from standard digital sensors must be encoded into spike trains before it can be elaborated with neuromorphic computing technologies. We present here a detailed comparison of available spike encoding techniques for the translation of time-varying signals into the event-based signal domain, tested on two different datasets both acquired through commercially available digital devices: the Free Spoken Digit dataset (FSD), consisting of 8-kHz audio files, and the WISDM dataset, composed of 20-Hz recordings of human activity through mobile and wearable inertial sensors. We propose a complete pipeline to benchmark these encoding techniques by performing time-dependent signal classification through a Spiking Convolutional Neural Network (sCNN), including a signal preprocessing step consisting of a bank of filters inspired by the human cochlea, feature extraction by production of a sonogram, transfer learning via an equivalent ANN, and model compression schemes aimed at resource optimization. The resulting performance comparison and analysis provides a powerful practical tool, empowering developers to select the most suitable coding method based on the type of data and the desired processing algorithms, and further expands the applicability of neuromorphic computational paradigms to embedded sensor systems widely employed in the IoT and industrial domains.

Integrate-and-fire circuit for converting analog signals to spikes using phase encoding *

“…Thus, the best-suited temporal approach for these applications is phase encoding, as ISI and temporal contrast lack a signal that serves as reference over the time dimension. Additionally, the results in [30] show the benefits of phase encoding in terms of accuracy and efficiency. The benefits are more clear when comparing with rate-coded approaches, as phase coding needs down to 6.5 times less spike operations for processing data [33], resulting in a lower energy footprint [19].…”

“…The authors in [27] and [28] introduce silicon neurons for generating different spike bursting behaviours, similar to those observed in biological neurons. We refer the interested reader to [29] for getting an overview of the different analog circuits used in neuromorphic systems for real-time applications, and to [30] for a comparison of the different encoding approaches. Some neuromorphic applications focus on generating the frequency spectrum of the incoming signal [24,31,32].…”

Integration of neuromorphic AI in event-driven distributed digitized systems: Concepts and research directions

“…Therefore, in order to gain analogous benefits in the subsequent processing, it is likely necessary to incorporate some degree of spike-timing code in neuromorphic processing systems. However, the choice of coding scheme is likely to be task-specific and subject to optimization (Guo W. et al, 2021;Forno et al, 2022;. or analog circuitry, and the temporal encoding may, again to varying degrees, asynchronously rely on the precise timings of spikes in qualitatively different coding schemes, see Table 2.…”

Efficiency metrics for auditory neuromorphic spike encoding techniques using information theory

“…decoding) some piece of information about the original stimulus from the spikes. For example, speech classification is used in [42] to compare three auditory SNN front-ends, and in [44] and [10] to evaluate multiple spike encoding techniques. Stimulus reconstruction, on the other hand, is used for example in [28] and [6] to compare several spike encoding techniques.…”

“…In contrast to decoding, information theory measures the total information captured by the spikes without introducing models or additional processing that can cause information loss. Information theory has been used for example in [7] and [10] to evaluate spike encoding techniques.…”