{"ID":2863444,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24495","arxiv_id":"2509.24495","title":"Neuroplasticity-inspired dynamic ANNs for multi-task demand forecasting","abstract":"This paper introduces a novel approach to Dynamic Artificial Neural Networks (D-ANNs) for multi-task demand forecasting called Neuroplastic Multi-Task Network (NMT-Net). Unlike conventional methods focusing on inference-time dynamics or computational efficiency, our proposed method enables structural adaptability of the computational graph during training, inspired by neuroplasticity as seen in biological systems. Each new task triggers a dynamic network adaptation, including similarity-based task identification and selective training of candidate ANN heads, which are then assessed and integrated into the model based on their performance. We evaluated our framework using three real-world multi-task demand forecasting datasets from Kaggle. We demonstrated its superior performance and consistency, achieving lower RMSE and standard deviation compared to traditional baselines and state-of-the-art multi-task learning methods. NMT-Net offers a scalable, adaptable solution for multi-task and continual learning in time series prediction. The complete code for NMT-Net is available from our GitHub repository.","short_abstract":"This paper introduces a novel approach to Dynamic Artificial Neural Networks (D-ANNs) for multi-task demand forecasting called Neuroplastic Multi-Task Network (NMT-Net). Unlike conventional methods focusing on inference-time dynamics or computational efficiency, our proposed method enables structural adaptability of th...","url_abs":"https://arxiv.org/abs/2509.24495","url_pdf":"https://arxiv.org/pdf/2509.24495v1","authors":"[\"Mateusz Żarski\",\"Sławomir Nowaczyk\"]","published":"2025-09-29T09:08:08Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}