Affect and Effect: Limitations of regularisation-based continual learning in EEG-based emotion classification
NegativeArtificial Intelligence
- A recent study highlights the limitations of regularisation-based continual learning methods in EEG-based emotion classification, particularly in generalising to unseen subjects. The research indicates that approaches like Elastic Weight Consolidation and Synaptic Intelligence prioritize mitigating catastrophic forgetting over adapting to new subjects, resulting in suboptimal performance on the DREAMER and SEED datasets.
- This finding is significant as it challenges the effectiveness of established continual learning methods in a field where accurate emotion recognition is crucial for applications such as mental health monitoring and human-computer interaction.
- The ongoing struggle with inter-and intra-subject variability in EEG data underscores a broader challenge in emotion recognition technologies, prompting the exploration of alternative models and strategies, such as adversarial training and multi-source domain adaptation, to enhance classification accuracy across diverse populations.
— via World Pulse Now AI Editorial System