Fading memory as inductive bias in residual recurrent networks.

Residual connections have been proposed as an architecture-based inductive bias to mitigate the problem of exploding and vanishing gradients and increased task performance in both feed-forward and recurrent networks (RNNs) when trained with the backpropagation algorithm. Yet, little is known about how residual connections in RNNs influence their dynamics and fading memory properties. Here, we introduce weakly coupled residual recurrent networks (WCRNNs) in which residual connections result in well-defined Lyapunov exponents and allow for studying properties of fading memory.

A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations.

Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Furthermore, CNNs have major applications in understanding the nature of visual representations in the human brain. Yet it remains poorly understood how CNNs actually make their decisions, what the nature of their internal representations is, and how their recognition strategies differ from humans.

Modern Artificial Neural Networks: Is Evolution Cleverer?

Machine learning tools, particularly artificial neural networks (ANN), have become ubiquitous in many scientific disciplines, and machine learning-based techniques flourish not only because of the expanding computational power and the increasing availability of labeled data sets but also because of the increasingly powerful training algorithms and refined topologies of ANN. Some refined topologies were initially motivated by neuronal network architectures found in the brain, such as convolutional ANN. Later topologies of neuronal networks departed from the biological substrate and began to be developed independently as the biological processing units are not well understood or are not transferable to in silico architectures.

Crystalline and magnetic properties of CoO nanoparticles locally investigated by using radioactive indium tracer.

We herein report a comprehensive investigation on the magnetic, structural, and electric properties of CoO nanoparticles with different sizes by local inspection through hyperfine interactions measured in a wide range of temperatures (10-670 K) by using radioactive [Formula: see text]In([Formula: see text]Cd) tracers with the perturbed angular correlations technique. Small cobalt oxide nanoparticles with the characteristic size of 6.5 nm have been prepared by the wet chemical route that turned out to be essential to incorporate radioactivity tracers during nucleation and growth of the particles.

Ray-tracing simulation of the radiation dose distribution on the surface of the spherical phantom of the MATROSHKA-R experiment onboard the ISS.

Space radiation is one of the main concerns for human space flights. The prediction of the radiation dose for the actual spacecraft geometry is very important for the planning of long-duration missions. We present a numerical method for the fast calculation of the radiation dose rate during a space flight.