With the adoption of smart systems, artificial neural networks (ANNs) have become ubiquitous. Conventional ANN implementations have high energy consumption, limiting their use in embedded and mobile applications. Spiking neural networks (SNNs) mimic the dynamics of biological neural networks by distributing information over time through binary spikes. Neuromorphic hardware has emerged to leverage the characteristics of SNNs, such as asynchronous processing and high activation sparsity. Therefore, SNNs have recently gained interest in the machine learning community as a brain-inspired alternative to ANNs for low-power applications. However, the discrete representation of the information makes the training of SNNs by backpropagation-based techniques challenging. In this survey, we review training strategies for deep SNNs targeting deep learning applications such as image processing. We start with methods based on the conversion from an ANN to an SNN and compare these with backpropagation-based techniques. We propose a new taxonomy of spiking backpropagation algorithms into three categories, namely, spatial, spatiotemporal, and single-spike approaches. In addition, we analyze different strategies to improve accuracy, latency, and sparsity, such as regularization methods, training hybridization, and tuning of the parameters specific to the SNN neuron model. We highlight the impact of input encoding, network architecture, and training strategy on the accuracy–latency tradeoff. Finally, in light of the remaining challenges for accurate and efficient SNN solutions, we emphasize the importance of joint hardware–software codevelopment.

Spiking Neural Networks (SNNs) hold the promise of lower energy consumption in embedded hardware due to their spike-based computations compared to traditional Artificial Neural Networks (ANNs). The relative energy efficiency of this emerging technology compared to traditional digital hardware has not been fully explored. Many studies do not consider memory accesses, which account for an important fraction of the energy consumption, use naive ANN hardware implementations, or lack generality. In this paper, we compare the relative energy efficiency of classical digital implementations of ANNs with novel event-based SNN implementations based on variants of the Integrate and Fire (IF) model. We provide a theoretical upper bound on the relative energy efficiency of ANNs, by computing the maximum possible benefit from ANN data reuse and sparsity. We also use the Eyeriss ANN accelerator as a case study. We show that the simpler IF model is more energy-efficient than the Leaky IF and temporal continuous synapse models. Moreover, SNNs with the IF model can compete with efficient ANN implementations when there is a very high spike sparsity, i.e. between 0.15 and 1.38 spikes per synapse per inference, depending on the ANN implementation. Our analysis shows that hybrid ANN-SNN architectures, leveraging a SNN event-based approach in layers with high sparsity and ANN parallel processing for the others, are a promising new path for further energy savings.

Deep Neural Networks (DNNs) are increasingly used in safety critical autonomous systems. We present MOZART+, a DNN accelerator architecture which provides fault detection and fault tolerance. MOZART+ is a systolic architecture based on the Output Stationary (OS) data-flow, as it is a data-flow that inherently limits fault propagation. In addition, MOZART+ achieves fault detection with on-line functional testing of the Processing Elements (PEs). Faulty PEs are swiftly taken off-line with minimal classification impact. We show how to handle the case of layers with a small number of neurons. The implementation of our approach on Squeezenet results in a loss of accuracy of less than 3% in the presence of a single faulty PE, compared to 15-33% without mitigation. The area overhead for the test logic does not exceed 8%. Dropout during training further improves fault tolerance, without a priori knowledge of the faults. We present a detailed fault-injection study on multiple systolic architectures, considering different fault-models and comparing different measures of accuracy.

Unbiased sources of true randomness are critical for the successful deployment of stochastic unconventional computing schemes and encryption applications in hardware. Leveraging nanoscale thermal magnetization fluctuations provides an efficient and almost costfree means of generating truly random bitstreams, distinguishing them from predictable pseudorandom sequences. However, existing approaches that aim to achieve randomness often suffer from bias, leading to significant deviations from equal fractions of 0 and 1 in the bitstreams and compromising their inherent unpredictability. This study presents a hardware approach that capitalizes on the intrinsic balance of phase noise in an oscillator injection-locked at twice its natural frequency, leveraging the stability of this naturally balanced physical system. We demonstrate the successful generation of unbiased and truly random bitstreams through extensive experimentation. Our numerical simulations exhibit excellent agreement with the experimental results, confirming the robustness and viability of our approach.

This paper presents a methodology for analyzing the behavior of nanometer technologies regarding "multiple event transients" (MET) caused by nuclear reaction induced by atmospheric neutrons. For the first time, currents collected by several sensitive areas of an ASIC cell resulting from a nuclear reaction are addressed by simulation. Libraries of several thousand types of currents are obtained for neutron energy range between 1 and 200 MeV. Group of currents are simultaneously injected at SPICE level and their effects are monitored on the cell output. Following an amplitude criterion, output transient duration and associated occurrence probability are recorded. A 130 nm NAND gate from ATMEL Corporation is first used to illustrate the methodology and a comparison between single event transients and multiple event transients effects is presented Finally, results regarding five different combinational cells in the ATMEL 130 nm library are presented and discussed.