The field of Deep Learning (DL) has seen a remarkable series of developments with increasingly accurate and robust algorithms. However, the increase in performance has been accompanied by an increase in the parameters, complexity, and training and inference time of the models, which means that we are rapidly reaching a point where DL may no longer be feasible. On the other hand, some specific applications need to be carefully considered when developing DL models due to hardware limitations or power requirements. In this context, there is a growing interest in efficient DL algorithms, with Spiking Neural Networks (SNNs) being one of the most promising paradigms. Due to the inherent asynchrony and sparseness of spike trains, these types of networks have the potential to reduce power consumption while maintaining relatively good performance. This is attractive for efficient DL and if successful, could replace traditional Artificial Neural Networks (ANNs) in many applications. However, despite significant progress, the performance of SNNs on benchmark datasets is often lower than that of traditional ANNs. Moreover, due to the non-differentiable nature of their activation functions, it is difficult to train SNNs with direct backpropagation, so appropriate training strategies must be found. Nevertheless, significant efforts have been made to develop competitive models. This survey covers the main ideas behind SNNs and reviews recent trends in learning rules and network architectures, with a particular focus on biologically inspired strategies. It also provides some practical considerations of state-of-the-art SNNs and discusses relevant research opportunities.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09787485.pdf

Spiking Neural Networks: A Survey

The development of advanced autonomous driving applications is hindered by the complex temporal structure of sensory data, as well as by the limited computational and energy resources of their on-board systems. Currently, neuromorphic engineering is a rapidly growing field that aims to design information processing systems similar to the human brain by leveraging novel algorithms based on spiking neural networks (SNNs). These systems are well-suited to recognize temporal patterns in data while maintaining a low energy consumption and offering highly parallel architectures for fast computation. However, the lack of effective algorithms for SNNs impedes their wide usage in mobile robot applications. This paper addresses the problem of radar signal processing by introducing a novel SNN that substitutes the discrete Fourier transform and constant false-alarm rate algorithm for raw radar data, where the weights and architecture of the SNN are derived from the original algorithms. We demonstrate that our proposed SNN can achieve competitive results compared to that of the original algorithms in simulated driving scenarios while retaining its spike-based nature.

/pdf/spiking-neural-network-for-fourier-transform-and-object-3t29svvlz0.pdf

Spiking Neural Network for Fourier Transform and Object Detection for Automotive Radar.

Though neuromorphic computers have typically targeted applications in machine learning and neuroscience (‘cognitive’ applications), they have many computational characteristics that are attractive for a wide variety of computational problems. In this work, we review the current state-of-the-art for non-cognitive applications on neuromorphic computers, including simple computational kernels for composition, graph algorithms, constrained optimization, and signal processing. We discuss the advantages of using neuromorphic computers for these different applications, as well as the challenges that still remain. The ultimate goal of this work is to bring awareness to this class of problems for neuromorphic systems to the broader community, particularly to encourage further work in this area and to make sure that these applications are considered in the design of future neuromorphic systems.

A review of non-cognitive applications for neuromorphic computing

Spiking neural P systems (abbreviated as SNP systems) are models of computation that mimic the behavior of biological neurons. The spiking neural P systems with communication on request (abbreviated as SNQP systems) are a recently developed class of SNP system, where a neuron actively requests spikes from the neighboring neurons instead of passively receiving spikes. It is already known that small SNQP systems, with four unbounded neurons, can achieve Turing universality. In this context, 'unbounded' means that the number of spikes in a neuron is not capped. This work investigates the dependency of the number of unbounded neurons on the computation capability of SNQP systems. Specifically, we prove that (1) SNQP systems composed entirely of bounded neurons can characterize the family of finite sets of numbers; (2) SNQP systems containing two unbounded neurons are capable of generating the family of semilinear sets of numbers; (3) SNQP systems containing three unbounded neurons are capable of generating nonsemilinear sets of numbers. Moreover, it is obtained in a constructive way that SNQP systems with two unbounded neurons compute the operations of Boolean logic gates, i.e., OR, AND, NOT, and XOR gates. These theoretical findings demonstrate that the number of unbounded neurons is a key parameter that influences the computation capability of SNQP systems.

On the Tuning of the Computation Capability of Spiking Neural Membrane Systems with Communication on Request

Frequency-modulated continuous wave radar sensors play an essential role for assisted and autonomous driving as they are robust under all weather and light conditions. However, the rising number of transmitters and receivers for obtaining a higher angular resolution increases the cost for digital signal processing. One promising approach for energy-efficient signal processing is the usage of brain-inspired spiking neural networks (SNNs) implemented on neuromorphic hardware. In this article we perform a step-by-step analysis of automotive radar processing and argue how spiking neural networks could replace or complement the conventional processing. We provide SNN examples for two processing steps and evaluate their accuracy and computational efficiency. For radar target detection, an SNN with temporal coding is competitive to the conventional approach at a low compute overhead. Instead, our SNN for target classification achieves an accuracy close to a reference artificial neural network while requiring 200 times less operations. Finally, we discuss the specific requirements and challenges for SNN-based radar processing on neuromorphic hardware. This study proves the general applicability of SNNs for automotive radar processing and sustains the prospect of energy-efficient realizations in automated vehicles.

Automotive Radar Processing With Spiking Neural Networks: Concepts and Challenges

Biologically inspired spiking neural networks are increasingly popular in the field of artificial intelligence due to their ability to solve complex problems while being power efficient. They do so by leveraging the timing of discrete spikes as main information carrier. Though, industrial applications are still lacking, partially because the question of how to encode incoming data into discrete spike events cannot be uniformly answered. In this paper, we summarise the signal encoding schemes presented in the literature and propose a uniform nomenclature to prevent the vague usage of ambiguous definitions. Therefore we survey both, the theoretical foundations as well as applications of the encoding schemes. This work provides a foundation in spiking signal encoding and gives an overview over different application-oriented implementations which utilise the schemes.

/pdf/a-survey-of-encoding-techniques-for-signal-processing-in-4nystb4n3x.pdf

A Survey of Encoding Techniques for Signal Processing in Spiking Neural Networks

The growing demand for complex computations in edge devices requires the development of algorithms and hardware accelerators that are powerful while remaining energy-efficient. A possible solution are spiking neural networks, as they have been demonstrated to be energy-efficient in several data processing and classification tasks when executed on specialized neuromorphic hardware. In the field of speech processing, they are especially suited for the online classification of audio streams due to their strong temporal affinity. However, so far, there has been a lack of emphasis on small-scale networks that will ultimately fit into restricted neuromorphic implementations. We propose the use of resonating neurons as an input layer to spiking neural networks for online audio classification to enable an end-to-end solution. We compare different architectures to the established method of using mel-frequency-based spectral features. With our approach, spiking neural networks can be directly used without additional preprocessing, thereby making them suitable for simple continuous low-power analysis of audio streams. We compare the classification accuracy of different network architectures with ours in a keyword spotting benchmark to demonstrate the performance of our approach.

End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons

Spiking neural networks offer the potential to drastically reduce energy consumption in edge devices. Unfortunately they are overshadowed by today's common analog neural networks, whose superior backpropagation-based learning algorithms frequently demonstrate superhuman performance on different tasks. The best accuracies in spiking networks are achieved by training analog networks and converting them. Still, during runtime many simulation time steps are needed until they converge. To improve the simulation time we evaluate two inference optimization algorithms and propose an additional method for error minimization. We assess them on Residual Networks of different sizes, up to ResNet101. The combination of all three is evaluated on a large scale with a RetinaNet on the COCO dataset. Our experiments show that all optimization algorithms combined can speed up the inference process by a factor of ten. Additionally, the accuracy loss between the original and the converted network is less than half a percent, which is the lowest on a complex dataset reported to date.

Minimizing Inference Time: Optimization Methods for Converted Deep Spiking Neural Networks

FMCW radar sensors receive target reflections from the environmental surrounding at frequencies around 77 GHz. The increasing number of sensors on the road operating in this frequency range leads to a higher likelihood of unfavorable radar-to-radar interference. Consequences can be the appearance of artificial targets or the degradation of the noise spectrum, where targets with a small RCS might disappear. We use a Neural Network-based outlier detection method to identify corrupted samples in the time domain signal after the ADC. The architecture consists of a recurrent Neural Network with Long-Short-Term-Memory cells to extract the temporal information. The small network and the stream processing make it suitable for embedded devices. The semi-supervised trained network can detect various interference patterns with reduced training effort. We evaluate the system in a complete pipeline with zeroing mitigation on simulated randomized FMCW data. The method increases the Signal-to-Noise-Ratio ratio by up to 30 dB in the presence of interference and increases the overall system performance and reliability.

Daniel Auge

Papers

A Survey of Encoding Techniques for Signal Processing in Spiking Neural Networks

Automotive Radar Processing With Spiking Neural Networks: Concepts and Challenges

End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons

Minimizing Inference Time: Optimization Methods for Converted Deep Spiking Neural Networks

FMCW radar2radar Interference Detection with a Recurrent Neural Network