Estimation is a canonical problem in sensor networks. The intrinsic nature of sensor networks requires estimation algorithms based on sensor data to be distributed and recursive; such algorithms are studied in this chapter for the problem of (conditional) least squares estimation. The chapter is divided into three parts. In the first part, distributed and recursive estimation algorithms are dev...

Binary neural networks (BNNs) are an extremely promising method for reducing deep networks’ complexity and power consumption significantly. Binarization techniques, however, suffer from ineligible performance degradation compared to their full-precision counterparts. Prior work mainly focused on strategies sign function approximation during the forward backward phases reduce quantization error ...

The cloud-based solutions are becoming inefficient due to considerably large time delays, high power consumption, and security privacy concerns caused by billions of connected wireless devices typically zillions bytes data they produce at the network edge. A blend edge computing Artificial Intelligence (AI) techniques could optimally shift resourceful computation servers closer edge, which prov...