Advancing broad learning through structured feature generation
Mario Mallea, Àngela Nebot, Francisco Mugica · Expert Systems with Applications · 2025
• Tackles randomness redundancy in broad learning systems with structured design. • Improves accuracy compared to classic broad learning systems in classification and regression tasks. • Addresses the lack of robustness in random neural architectures when faced with noise and scarce data. • Structured network design produces interpretable feature maps, enabling transparent AI decisions. Deep neural networks achieve strong performance in big data scenarios, while requiring extensive iterative parameter optimization, making them inefficient and suboptimal in scarce data scenarios. Broad Learning System (BLS) has gained popularity as an efficient, effective, and incremental learning model. BLS relies on independent and identically distributed random feature generation. Although efficient, the literature has shown that this approach can lead to suboptimal and redundant representations. This paper introduces Structured BLS (SBLS), a novel reinterpretation of BLS components. SBLS enhances latent features by incorporating a structured random basis, which provides a beneficial inductive bias that promotes neuronal specialization to learn specific patterns in the data while reducing the redundancy issue of the classic BLS. Experimental results in various classification and regression datasets demonstrate that SBLS outperforms BLS in terms of performance, robustness to noise, and interpretability, while remaining efficient and easy to deploy. Our findings emphasize the need for focused feature generation through random weights in neural networks and reservoir computing. In fact, we are transitioning from a chaotic to a controlled exploration of patterns. Moreover, we illustrate how our approach can incorporate task-specific knowledge into neuron behavior by design. SBLS has practical implications for real-world applications that involve data scarcity. By refining the way randomness is exploited in neural networks, our work challenges the conventional wisdom that improved performance requires deeper architectures or complex optimization strategies. Instead, we show that intelligent feature generation can unlock significant gains at minimal additional cost. 1