Results 131 to 140 of about 119,888 (330)
A Degeneracy Framework for Scalable Graph Autoencoders
, 2019 In this paper, we present a general framework to scale graph autoencoders (AE) and graph variational autoencoders (VAE). This framework leverages graph degeneracy concepts to train models only from a dense subset of nodes instead of using the entire ...
Hennequin, Romain +3 more
core
MGDP: Mastering a Generalized Depth Perception Model for Quadruped Locomotion
Advanced Science, EarlyView.ABSTRACT Perception‐based Deep Reinforcement Learning (DRL) controllers demonstrate impressive performance on challenging terrains. However, existing controllers still face core limitations, struggling to achieve both terrain generality and platform transferability, and are constrained by high computational overhead and sensitivity to sensor noise.
Yinzhao Dong +9 more
wiley +1 more source
PAIR: Reconstructing Single‐Cell Open‐Chromatin Landscapes for Transcription Factor Regulome Mapping
Advanced Science, EarlyView.scATAC‐seq analysis is often constrained by limited sequencing depth, extreme sparsity, and pervasive technical missingness. PAIR is a probabilistic framework that restores scATAC‐seq accessibility profiles by directly modeling the native cell–peak bipartite structure of chromatin accessibility.
Yanchi Su +7 more
wiley +1 more source
PLoS ONE, 2017 The application of deep learning approaches to finance has received a great deal of attention from both investors and researchers. This study presents a novel deep learning framework where wavelet transforms (WT), stacked autoencoders (SAEs) and long ...
Wei Bao, Jun Yue, Yulei Rao
semanticscholar +1 more source
Advanced Science, EarlyView.SpaMode introduces a versatile framework for spatial multi‐omics integration across vertical, horizontal, and mosaic scenarios. By disentangling modality‐invariant and variant features through a mixture‐of‐experts mechanism, it adaptively reconfigures spatially heterogeneous signals.
Xubin Zheng +6 more
wiley +1 more source
Advanced Science, EarlyView.A self‐supervised multi‐view graph fusion framework integrates spatial multi‐omics, excelling in domain identification and denoising. It reconstructs spatial pseudo‐expression, jointly analyzes multi‐omics data, infers RNA velocity, predicts spatial omics features from single‐cell multi‐omics, and detects spatially dark genes and transcription factors,
Yuejing Lu +8 more
wiley +1 more source
Advanced Science, EarlyView.STAID is a unified deep learning framework that couples iterative pseudo‐spot refinement with neural network training through a feedback loop and exploits gene co‐expression information to model higher‐order interactions, achieving accurate and robust cell‐type deconvolution in spatial transcriptomics.
Jixin Liu +5 more
wiley +1 more source
Resampled Priors for Variational Autoencoders
, 2018 We propose Learned Accept/Reject Sampling (LARS), a method for constructing richer priors using rejection sampling with a learned acceptance function. This work is motivated by recent analyses of the VAE objective, which pointed out that commonly used ...
Bauer, Matthias, Mnih, Andriy
core
Roadmap for High‐Throughput Ceramic Materials Synthesis and Discovery for Batteries
Advanced Energy Materials, EarlyView.This work examines ceramic synthesis through the lens of high‐throughput synthesis and optimization, identifying opportunities for faster, adaptable routes. It emphasizes flexible liquid precursor–to–solid film methods over slower solid‐state approaches and highlights computer‐aided decision making to optimize both material properties and device ...
Jesse J. Hinricher +10 more
wiley +1 more source