Computation Control Protocol (CCP) google
Cooperative computation is a promising approach for localized data processing for Internet of Things (IoT), where computationally intensive tasks in a device could be divided into sub-tasks, and offloaded to other devices or servers in close proximity. However, exploiting the potential of cooperative computation is challenging mainly due to the heterogeneous nature of IoT devices. Indeed, IoT devices may have different and time-varying computing power and energy resources, and could be mobile. Coded computation, which advocates mixing data in sub-tasks by employing erasure codes and offloading these sub-tasks to other devices for computation, is recently gaining interest, thanks to its higher reliability, smaller delay, and lower communication costs. In this paper, we develop a coded cooperative computation framework, which we name Computation Control Protocol (CCP), by taking into account heterogeneous computing power and energy resources of IoT devices. CCP dynamically allocates sub-tasks to helpers and is adaptive to time-varying resources. We show that (i) CCP improves task completion delay significantly as compared to baselines, (ii) task completion delay of CCP is very close to its theoretical characterization, and (iii) the efficiency of CCP in terms of resource utilization is higher than 99%, which is significant. …

Wiener-Filter google
In signal processing, the Wiener Filter (Wiener-Kolmogorov Filter) is a filter used to produce an estimate of a desired or target random process by linear time-invariant filtering of an observed noisy process, assuming known stationary signal and noise spectra, and additive noise. The Wiener filter minimizes the mean square error between the estimated random process and the desired process. …

Deep-Shallow Incremental Learning (DeeSIL) google
Incremental Learning (IL) is an interesting AI problem when the algorithm is assumed to work on a budget. This is especially true when IL is modeled using a deep learning approach, where two complex challenges arise due to limited memory, which induces catastrophic forgetting and delays related to the retraining needed in order to incorporate new classes. Here we introduce DeeSIL, an adaptation of a known transfer learning scheme that combines a fixed deep representation used as feature extractor and learning independent shallow classifiers to increase recognition capacity. This scheme tackles the two aforementioned challenges since it works well with a limited memory budget and each new concept can be added within a minute. Moreover, since no deep retraining is needed when the model is incremented, DeeSIL can integrate larger amounts of initial data that provide more transferable features. Performance is evaluated on ImageNet LSVRC 2012 against three state of the art algorithms. Results show that, at scale, DeeSIL performance is 23 and 33 points higher than the best baseline when using the same and more initial data respectively. …

Advertisements