This paper is a review of the evolutionary history of deep learning models. It covers from the
genesis of neural networks when associationism modeling of the brain is studied, to the …

Designing and constructing bifunctional electrocatalysts is vital for water splitting. Particularly,
the rational interface engineering can effectively modify the active sites and promote the …

We investigate the relationship between the frequency spectrum of image data and the
generalization behavior of convolutional neural networks (CNN). We first notice CNN's ability in …

Constructing high-efficiency electrocatalysts is vital towards electrocatalytic water splitting,
but it remains a challenge. Although Ni-based materials have drawn extensive attention as …

Nanotube arrays have shown great potential in a variety of important applications, such as
hybrid supercapacitors. In order to endow nanotubes with multifunctionality, rationally …

Convolutional Neural Networks (CNN) conduct image classification by activating dominant
features that correlated with labels. When the training and testing data are under similar …

Ceramics and ceramic-based composites have been widely used in electronic information
and communication, chemical industry, instrument manufacturing and other fields. However, …

Diverse quantitative models have been applied to analyse emission trading system, as the
top effective climate change policy. This paper aims to present a comprehensive literature …

Despite their renowned in-domain predictive power, convolutional neural networks are
known to rely more on high-frequency patterns that humans deem superficial than on low-…

Developing efficient and low-cost electrocatalysts for the oxygen evolution reaction and
hydrogen evolution reaction is urgently needed for overall water splitting. Herein, three …