9/14/2023 0 Comments Hyperdimensional space billiards![]() Meanwhile, multi-task learning (MTL) is grabbing attention recently since a single model can accommodate multiple cognitive tasks is more desirable for the future of IoT. This brings out numerous advantages, including lower latency, user security, and cost savings. In the era of IoT, edge computing with energy-efficient machine learning models keeps data processing close to end-users. Compared with the baseline method, our approach efficiently utilizes the unused capacity in the hyperspace and shows a 12.8% improvement in averaged accuracy with negligible memory overhead. ![]() To mitigate the interferences between different tasks, we project each task into a separate subspace for learning. In this paper, we propose Task-Projected Hyperdimensional Computing (TP-HDC) to make the HD model simultaneously support multiple tasks by exploiting the redundant dimensionality in the hyperspace. To the best of our knowledge, no study has been conducted to investigate the feasibility of applying multi-task learning to HD computing. The model forgets the knowledge learned from previous tasks and only focuses on the current one. ![]() However, an HD model incrementally trained on multiple tasks suffers from the negative impacts of catastrophic forgetting. As an energy-efficient and fast learning computational paradigm, HD computing has shown great success in many real-world applications. Brain-inspired Hyperdimensional (HD) computing is an emerging technique for cognitive tasks in the field of low-power design. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |