TL;DR: Shem is presented, a framework that enables gradient-based optimization of system-level objectives such as robustness and accuracy on user-defined analog compute models and introduces an autoparallelization algorithm that reduces total optimization runtime by 49–91%.
Analog compute paradigms are gaining attention for their potential to overcome the energy and latency limits of digital systems. Analog computations are modeled as dynamical systems for design and optimization, but this process is challenging: the dynamics are governed by nonlinear differential equations without closed-form solutions, are susceptible to hardware nonidealities such as mismatch and noise, and rely on digitally programmable interfaces that complicate system-level reasoning. We present Shem , a framework that enables gradient-based optimization of system-level objectives such as robustness and accuracy on user-defined analog compute models. We leverage the fact that analog compute models are inherently differentiable, and that nonidealities and digital interfaces can be approximated by differentiable functions, making gradient descent a natural and unified approach for optimization. We evaluate Shem across diverse case studies, including an oscillator-based pattern recognizer, a cellular nonlinear network edge detector, an analog-to-information converter integrated with a neural network, and a transmission-line security primitive. In all cases, Shem improves application performance, including signal-to-noise ratio, classification accuracy, and a security metric. In addition, we introduce an autoparallelization algorithm that reduces total optimization runtime by 49–91%.
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: 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-…
TL;DR: This work proposes heterogeneous neural networks that combine spiking neural networks (SNNs) and artificial neural networks (ANNs) at bandwidth-limited regions, such as chip boundaries, where spike-based communication reduces data transfer overhead.
Efficient communication is central to both biological and artificial intelligence (AI) systems. In biological brains, the challenge of long-range communication across regions is addressed through sparse, spike-based signaling, minimizing energy and latency. Conversely, modern AI…
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…
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…