Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3 × 3) kernels. This paper describes a method for learning the kernels to provide varying in layer. The utilizes differentiable, therefore backpropagation-trainable Gaussian envelope which can grow or shrink base grid. Our experiments compared proposed adaptive ordinary convolution simple t...

Internet-of-Things (IoT) technology is envisioned to enable a variety of real-time applications by interconnecting billions sensors/devices. These IoT devices rely on low-power wide-area wireless connectivity for transmitting, mostly fixed- but small-size, status updates the random processes observed them. Owing their ubiquity, cellular networks are seen as natural candidate providing reliable ...

Abstract Current algorithms for quantum state tomography (QST) are costly both on the experimental front, requiring measurement of many copies state, and classical computational needing a long time to analyze gathered data. Here, we introduce neural adaptive (NAQT), fast, flexible machine-learning-based algorithm QST that adapts measurements provides orders magnitude faster processing while ret...

The development of engineering applications of neural networks makes it necessary to clarify the similarities and differences between the concepts and methods developed for neural networks and those used in more classical fields such as filtering and control. In previous papers [Nerrand et al. 1993], [Marcos et al. 1993], the relationships between non-linear adaptive filters and neural networks...