Adapting Tensor Kernel Machines to Enable Efficient Transfer Learning for Seizure Detection
This work addresses the problem of resource-efficient seizure detection for wearable devices, offering an incremental improvement in transfer learning methods.
The paper tackles efficient transfer learning for seizure detection using an adaptive tensor kernel machine (Adapt-TKM), which personalizes patient-independent models with minimal patient-specific data, achieving better performance while reducing parameters by around 100 times compared to adaptive SVM models.
Transfer learning aims to optimize performance in a target task by learning from a related source problem. In this work, we propose an efficient transfer learning method using a tensor kernel machine. Our method takes inspiration from the adaptive SVM and hence transfers 'knowledge' from the source to the 'adapted' model via regularization. The main advantage of using tensor kernel machines is that they leverage low-rank tensor networks to learn a compact non-linear model in the primal domain. This allows for a more efficient adaptation without adding more parameters to the model. To demonstrate the effectiveness of our approach, we apply the adaptive tensor kernel machine (Adapt-TKM) to seizure detection on behind-the-ear EEG. By personalizing patient-independent models with a small amount of patient-specific data, the patient-adapted model (which utilizes the Adapt-TKM), achieves better performance compared to the patient-independent and fully patient-specific models. Notably, it is able to do so while requiring around 100 times fewer parameters than the adaptive SVM model, leading to a correspondingly faster inference speed. This makes the Adapt-TKM especially useful for resource-constrained wearable devices.