🤖 AI Summary
Spiking Neural Networks (SNNs) suffer from poor robustness under uncertain inputs and low training/inference efficiency. Method: We propose the first Forward-Forward Algorithm (FFA)-based framework jointly addressing out-of-distribution (OOD) detection and interpretability for fully spiking networks. Our approach introduces a gradient-free spike attribution mechanism that leverages FFA’s inherent sparse latent representations to model latent-variable densities, enabling simultaneous high-selectivity OOD likelihood estimation and pixel-level visual explanations. Results: Experiments on Omniglot, Not-MNIST, and CIFAR-10 benchmarks demonstrate significant improvements over state-of-the-art SNNs in OOD detection performance. The method precisely localizes anomalous regions—e.g., artifacts or missing patches—while preserving event-driven energy efficiency and strong model interpretability.
📝 Abstract
In recent years, Artificial Intelligence (AI) models have achieved remarkable success across various domains, yet challenges persist in two critical areas: ensuring robustness against uncertain inputs and drastically increasing model efficiency during training and inference. Spiking Neural Networks (SNNs), inspired by biological systems, offer a promising avenue for overcoming these limitations. By operating in an event-driven manner, SNNs achieve low energy consumption and can naturally implement biological methods known for their high noise tolerance. In this work, we explore the potential of the spiking Forward-Forward Algorithm (FFA) to address these challenges, leveraging its representational properties for both Out-of-Distribution (OoD) detection and interpretability. To achieve this, we exploit the sparse and highly specialized neural latent space of FF networks to estimate the likelihood of a sample belonging to the training distribution. Additionally, we propose a novel, gradient-free attribution method to detect features that drive a sample away from class distributions, addressing the challenges posed by the lack of gradients in most visual interpretability methods for spiking models. We evaluate our OoD detection algorithm on well-known image datasets (e.g., Omniglot, Not-MNIST, CIFAR10), outperforming previous methods proposed in the recent literature for OoD detection in spiking networks. Furthermore, our attribution method precisely identifies salient OoD features, such as artifacts or missing regions, hence providing a visual explanatory interface for the user to understand why unknown inputs are identified as such by the proposed method.