近年來,由神經網路實現的深度學習被廣泛地運用到各個領域。這些被用來解決各種問題的人工智慧演算法在使用上區分為兩個階段:首先必須經過學習階段(learning phase)得到一個模型,再進入推論階段(inference phase)得出最終結果。在我們的研究中,我們假設學習階段已經完成並專注在設計如何透過分散式運算的方式取代原有的集中式架構。我們利用霧運算的概念設計分散式系統,並將人工智慧演算法中的推論階段布建至階層式架構的霧節點之中。最後,我們會利用智慧商場當作應用情境,比較分散式和集中式兩種做法的差異,並驗證我們提出的分散式智能與霧運算結合的整體效能。
Deep learning enabled by neural networks has been proven to be an effective Artificial Intelligence (AI) algorithm in sophisticated applications. The algorithm is normally divided into two phases: learning phase and inference phase. In this research, we assume the learning phase is already accomplished offline and focus on expediting the inference phase by replacing the centralized processing of Cloud with the distributed processing of Fog. In our approach, inference algorithms in AI are distributed to multiple layers of Fog networking, constructed from oneM2M Middle Nodes. We verify the performance improvement of our proposed distributed AI/Fog system by comparing it against that of a Cloud-centric system based on a use case of smart shopping mall.