
Gradient boosting enhances physics-informed neural networks' performance by employing a sequence of neural networks.


coremsg

ensemble-learning-for-physics-informed-neural-networks-a-gradient-boosting-approach


Ensemble Learning for Physics Informed Neural Networks: A Gradient Boosting Approach


title_rewrite


Discovering slow invariant manifolds using a physics-informed neural network approach.


physics-informed-neural-network-for-slow-invariant-manifolds-in-stiff-odes


Physics-Informed Neural Network for Slow Invariant Manifolds in Stiff ODEs



This work integrates physics-derived memristor models into machine learning frameworks to address device nonidealities and improve neural network accuracy. The main thesis is to bring physical dynamics into consideration while modeling nonidealities in memristive devices to guide the development of future integrated devices.


integration-of-physics-derived-memristor-models-with-machine-learning-frameworks


Integration of Physics-Derived Memristor Models with Machine Learning Frameworks



The author proposes using an LSTM-based ML model to predict systemic errors in storm surge forecasting models, leading to improved accuracy by correcting biases.


storm-surge-modeling-in-the-ai-era-enhancing-forecasting-accuracy-with-lstm-based-machine-learning


Storm Surge Modeling in the AI Era: Enhancing Forecasting Accuracy with LSTM-Based Machine Learning
