TL;DR: This work presents a flexible, end-to-end workflow for the training, optimization, and deployment of SNNs across multiple neuromorphic hardware systems, with an emphasis on extensibility to future neuromorphic platforms.
Surrogate gradient methods have emerged as the dominant approach for enabling backpropagation for spiking neural networks (SNNs). However, many implementations are tightly coupled to target hardware platforms, constraining flexibility. In this work, we present a flexible, end-to-end workflow for the training, optimization, and deployment of SNNs across multiple neuromorphic hardware systems, with an emphasis on extensibility to future neuromorphic platforms. Our API integrates a modified implementation of SLAYER, a popular surrogate gradient descent approach, within the TENNLab neuromorphic software framework. We evaluate this workflow across multiple datasets, achieving competitive performance with state-of-the-art results, and we report energy metrics on custom neuromorphic hardware platforms.
TL;DR: A sleep-inspired, replay-driven memory consolidation-based temporal learning framework that reconstructs context from replayed memory during brief sleep periods for temporal context learning in resource-constrained edge systems is proposed.
In edge computing applications, storing long temporal sequences is memory and energy intensive, while sensory data arrives sequentially, requiring online learning. Although online updates reduce storage requirements, they lack access to broader temporal context needed for accurat…
TL;DR: A cross-layer fault simulation framework is developed that couples a gate-level model of the NoC with a high-level SNN simulator, enabling accurate propagation of hardware-level routing anomalies to SNN-level behavioral deviations.
The robustness of Spiking Neural Networks (SNNs) critically depends on the integrity of spike routing in neuromorphic hardware. While most prior work has focused on compute and memory faults, permanent faults in the Network-on-Chip (NoC) carrying the digital encoding of spike eve…
TL;DR: The entire SNN agent fits within a single Loihi 2 neuromorphic core, avoiding the inter-core routing and synchronization overhead that is often the real bottleneck on neuromorphic chips, and suggesting that neuromorphic hardware can host competitive, stable RTS agents.
Spiking neural networks (SNNs) have demonstrated competence in board games, but their application to real-time strategy (RTS) games—which demand simultaneous multi-unit control, resource management, and long-horizon planning—remains unexplored. We present the first SNN agent capa…
TL;DR: The research rigorously investigates how neuromorphic architectures encode and integrate temporal information by conducting a comprehensive ablation study using a hybrid network, and demonstrates that shallow neuromorphic integration effectively maximizes the gains from temporal integration while mitigating the information loss inherent in binary spike quantization.
While neuromorphic systems offer a promising path for processing dynamic, event-based data, current benchmarks often fail to isolate the specific impact of temporal integration on model performance. To address this, our research rigorously investigates how neuromorphic architectu…
TL;DR: CRISP (Compiled RISP) is a neuromorphic simulator based on RISP, which compiles a given network into a minimal sequence of machine code for the desired platform entirely at runtime.
Simulators for spiking neural networks lie on the critical path between a researcher with an idea and a working network. Many of the current simulators have various implementation inefficiencies that hamper their performance across a wide variety of tasks. CRISP (Compiled RISP) i…
TL;DR: This work adopts a biologically plausible saliency-informed dropout technique as an explainable alternative to the unstructured standard random dropout approach and presents empirical results on regimes where such structured dynamic and static sparsities interact optimally to prune a ResNet model on the Imagenette dataset.
Biological vision has evolved to make efficient use of the limited information processing capability and tight energy budget of the brain by preferentially processing the most salient features of visual scenes. In contrast, modern deep vision models rely on expansive, high-dimens…