Deep networks have been widely used in many domains in recent years. However, the pre-training of deep networks is time consuming with greedy layer-wise algorithm, and the scalability of this algorithm is greatly restricted by its inherently sequential nature where only one hidden layer can be trained at one time. In order to speed up the training of deep networks, this paper mainly focuses on ...

In network applications, it has become increasingly common to obtain datasets in the form of multiple networks observed on same set subjects, where each is obtained a related but different experiment condition or application scenario. Such can be modeled by multilayer layer separate itself while layers are associated and share some information. The present paper studies community detection styl...

Abstract Growth of ice crystals is ubiquitous around us, but we still do not know what occurring at the forefront crystallization. In general, interfacial structure inseparably involved in microscopic ordering during crystal growth. However, despite its importance nature and technology, intrinsic role melt growth remains to be elucidated. Here, using extensive molecular dynamics simulations, co...

The quantum approximate optimization algorithm (QAOA) is known for its capability and universality in solving combinatorial problems on near-term devices. results yielded by QAOA depend strongly initial variational parameters. Hence, parameter selection becomes an active area of research, as bad initialization might deteriorate the quality results, especially at great circuit depths. We first d...

Abstract Due to the nature of Selective Laser Melting process, built parts suffer from high chances defects formation. Powders quality have a significant impact on final attributes SLM-manufactured items. From processing standpoint, it is critical ensure proper powder distribution and compaction in each layer bed, which impacted by particle size distribution, packing density, flowability, spher...

Abstract. We test the reliability of two neural network interpretation techniques, backward optimization and layerwise relevance propagation, within geoscientific applications by applying them to a commonly studied geophysical phenomenon, Madden–Julian oscillation. The oscillation is multi-scale pattern tropical atmosphere that has been extensively over past decades, which makes it an ideal cas...