We introduce physics-informed neural networks –neural networks that are trained to solve supervised learning tasks while respecting any given laws of physics described by general nonlinear partial differential equations. In this work, we present our developments in the context of solving two main class...
the learning rules and the architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focu...
A deep reinforcement learning framework and its implementation for UAV-aided covert communication S. FU, Y. SU, Z. ZHANG and L. YIN Star point positioning for large dynamic star sensors in near space based on capsule network Z. LIAO, H. WANG, X. ZHENG, Y. ZANG, Y. LU and S. YAO ...
Continual learning is key to advancing machine learning,where information and experiences can be accumulated and used across tasks. This paper formulated progressive learning, a deep learning framework for continual learning that comprises three procedures: curriculum, progression, and pruning. Progressive ...
In this work, we proposed CAMP, a deep-learning framework for multi-level peptide–protein interaction prediction, including binary interaction prediction and peptide-binding residue prediction. We first generated a series of sequence-based features to construct feature profiles for peptides and proteins...
DEEP LEARNING FRAMEWORKINVERSE PROBLEMSPhysics-informed neural network (PINN) is an emerging technique for solving partial differential equations (PDEs) of flow... X Li,Y Liu,Z Liu - 《Physics of Fluids》 被引量: 0发表: 2023年 A class of improved fractional physics informed neural networks ?
Deep Learning Approaches Deep belief network (DBN, Jia, 2016; Huang, 2014) Stacked autoencoder (SAE, LV, 2015; Chen, 2016) --(not to extract spatial and temporal features jointly) Spatial: CNN Temporal: RNN CLTFP (2016, Wu&Tan, LSTM+1D-CNN) ...
sameerkhurana10/DSOL_rv0.2: DeepSol: A Deep Learning Framework for Sequence-Based Protein Solubility Prediction DeepSol: A deep learning framework for sequence-based protein solubility prediction. Bioinformatics, 1:9, 2018. doi: 10.1093/bioinformatics/bty166... ...
Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction 挑战: 首先,位置之间的空间依赖性仅依赖于历史交通的相似性,模型学习了静态空间依赖性。2)另一个局限性是,许多现有的研究忽略了长期周期性依赖的转移。交通数据具有很强的日周期性和周周期性,基于这种周期性的依赖性可以用于...
This section is dedicated to a computational assessment of the proposed deep learning memetic framework for solving the weighted vertex coloring problem and the conventional vertex coloring problem, by making comparisons with state-of-the-art methods. ...