✨ TL;DR
This paper applies Hebbian learning principles to audio classification in a continual learning setting, introducing a kernel plasticity approach that selectively updates network weights to balance learning new sounds while retaining knowledge of previously learned ones. On the ESC-50 dataset, the method achieves 76.3% accuracy across five incremental learning steps, significantly outperforming a baseline approach.
Deep neural networks typically suffer from catastrophic forgetting when learning new tasks sequentially—they lose performance on previously learned tasks when trained on new data. This is particularly problematic for continual or lifelong learning scenarios where systems need to incrementally acquire new knowledge without forgetting old information. While humans naturally perform lifelong learning, standard deep learning approaches struggle with this capability, especially in domains like audio classification where models need to continuously adapt to new sound categories.
The authors propose a Hebbian learning-based approach with kernel plasticity for incremental audio classification. The method selectively modulates network kernels (weights) during incremental learning steps: some kernels are actively updated to learn new information while others are protected to retain previous knowledge. This selective plasticity mechanism is inspired by biological learning processes in the brain, where synaptic connections strengthen or weaken based on correlated neural activity. The approach is evaluated on the ESC-50 environmental sound classification dataset, divided into five incremental learning steps to simulate continual learning scenarios.
What the paper shows.
The proposed kernel plasticity method achieves 76.3% overall accuracy across five incremental learning steps on the ESC-50 dataset. This represents a substantial improvement over the baseline approach without kernel plasticity, which only achieves 68.7% accuracy—an improvement of 7.6 percentage points. The method demonstrates significantly greater stability across tasks, indicating reduced catastrophic forgetting and better retention of previously learned sound categories throughout the incremental learning process.
The paper does not explicitly discuss limitations, but several can be inferred. The evaluation is limited to a single dataset (ESC-50) and a specific incremental learning protocol with five steps, which may not fully represent the diversity of continual learning scenarios. The paper does not provide detailed analysis of computational overhead introduced by the kernel plasticity mechanism or compare against other state-of-the-art continual learning methods beyond the basic baseline. Additionally, the scalability of the approach to larger numbers of incremental steps or more complex audio classification tasks remains unclear.
✨ Generated by Claude · Apr 21, 2026 · Read the PDF for authoritative content.