Distributed edge intelligence is a disruptive research area that enables the execution of machine learning and deep learning (ML/DL) algorithms close to where data are generated. Since edge devices are more limited and heterogeneous than typical cloud devices, many hindrances have to be overcome to fully extract the potential benefits of such an approach (such as data-in-motion analytics). In this paper, we investigate the challenges of running ML/DL on edge devices in a distributed way, paying special attention to how techniques are adapted or designed to execute on these restricted devices. The techniques under discussion pervade the processes of caching, training, inference, and offloading on edge devices. We also explore the benefits and drawbacks of these strategies.

No abstract

Subband structures are suitable for improving convergence properties of adaptive filtering algorithms, specially for colored input signals. This paper proposes a new subband adaptive algorithm with sparse adaptive subfilters, which employs the principle of minimal disturbance with multiple constraint optimization. A performance analysis is carried out, resulting in an expression for the steady-state mean-square error. It is shown that the proposed algorithm, under some particular parameter choices, presents the same performance as that of the normalized subband adaptive filter, but with reduced computational complexity.Index Terms-Adaptive filtering, subband structures, multirate processing.

No abstract