IEEE

A Prediction-Sampling-Based Multilayer-Structured Latent Factor Model for Accurate Representation to High-Dimensional and Sparse Data

Abstract: Performing highly accurate representation learning on a high-dimensional and sparse (HiDS) matrix is of great significance in a big data-related application such as a recommender system. A ...
IEEE

Switching Strategy to Reduce Inductor Current Ripple and Common Mode Voltage in Quasi Z-Source Ultra Sparse Matrix Converter

Abstract: This article aims to reduce the ripple current in the inductor used in a quasi Z-source ultra sparse matrix converter (USMC). The main limitations of the conventional USMC are limited ...
eLife

Barcode activity in a recurrent network model of the hippocampus enables efficient memory binding

The representation of individual memories in a recurrent neural network can be efficiently differentiated using chaotic recurrent dynamics.
TMCnet

MicroCloud Hologram Inc. Releases Learnable Quantum Spectral Filter Technology for Hybrid Graph Neural Networks

MicroCloud Hologram Inc. (NASDAQ: HOLO), ("HOLO" or the "Company"), a technology service provider, released learnable quantum spectral filter technology for hybrid graph neural networks. This ...