Weightless multi-class classifier ruled by “Mental images”

Common-sense rules represent a form of implicit knowledge derived from experience and observation, often used by both humans and artificial systems to guide decision-making. In this work, we introduce a novel extension of the DRASiW weightless neural network architecture that enables the automatic extraction of such rules from its internal knowledge representations, known as “Mental Images” (MIs). These rules, grounded in statistical patterns learned during training, are used to selectively inhibit a subset of discriminators prior to classification, effectively acting as a pre-filtering mechanism. The inhibition process is designed to reduce the computational burden and improve classification plausibility by narrowing the focus to the most promising classes. Unlike previous approaches that use MIs solely for interpretation or symbolic conversion, our method exploits this implicit knowledge to enhance the system’s own performance. The extracted rules reflect structural regularities within the input space and serve as a proxy for common sense reasoning embedded within the trained model. This work highlights how internal representations in weightless neural systems can be explicitly leveraged to support interpretable and efficient decision processes, bridging the gap between subsymbolic learning and symbolic reasoning through rule-based inhibition. • A novel extension of the DRASiW weightless neural network is proposed to extract common-sense rules from internal representations (“Mental Images”). • The extracted rules are used to inhibit subsets of discriminators during inference, improving classification performance and reducing computational cost. • Unlike previous approaches, the rules are not only interpretable but directly contribute to performance enhancement. • Extensive experiments on 77 datasets show measurable improvements in F1-score and accuracy across multiple WiSARD variants. • The proposed rule-guided inference bridges sub-symbolic and symbolic reasoning, offering a transparent and efficient hybrid classification model.