ansleywong Goto Github PK

automaticweightedloss

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

bayesianlstm

Bayesian LSTM (Tensorflow)

bidirectional-deep-readout-echo-state-network

Multi-variate time series classification with a bi-directional ESN with a readout implemented as a deep neural network.

deepxde

A library for scientific machine learning and physics-informed learning

demand_forecast

fpn_hsl-tfp

A Surrogate Model with Data Augmentation and Deep Transfer Learning for Temperature Field Prediction of Heat Source Layout

gaussian-processes-regression-tutorial

An Intuitive Tutorial to Gaussian Processes Regression

kalmanfilter

Testing Kalman Filter for GPS data

keras_gpyopt

Using Bayesian Optimization to optimize hyper parameter in Keras-made neural network model.

knn-tspi

K-Nearest Neighbors Time Series Prediction with Invariances

learning-python-physics-informed-machine-learning-pinns-deeponets

Physics Informed Machine Learning Tutorials (Pytorch and Jax)

lstm-svm-rf-time-series

Regression prediction of time series data using LSTM, SVM and random forest. 使用LSTM、SVM、随机森林对时间序列数据进行回归预测，注释拉满。

lstm_encoder_decoder

Build a LSTM encoder-decoder using PyTorch to make sequence-to-sequence prediction for time series data

mtl

Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics

pde-solvers

PDE Solvers: FEM vs Deep Learning

phylstm

We introduce an innovative physics-informed LSTM framework for metamodeling of nonlinear structural systems with scarce data.

physics-informed-neural-networks

Investigating PINNs

pinn-for-heat-transfer

Using PINN's to solve heat transfer problems for parameter

pinn-s-for-heat-transfer-problem

In recent years, the use of physics-informed neural networks (PINNs) has gained popularity across several engineering disciplines due to their effectiveness in solving linear and non-linear partial differential equations (PDE) and real-world problems despite noisy data. The basic approach used to solve the PINNs is to construct the neural network a

pinn_heat_transfer

PINN for heat transfer problems

pinn_heattransfer_tf2

Soving heat transfer problems using PINN with tf2.0

pinns

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

pinns-pytorch

PyTorch Implementation of Physics-informed Neural Networks

pinns-tf2.0

TensorFlow 2.0 implementation of Maziar Raissi's Physics Informed Neural Networks (PINNs).

sciann

Deep learning for Engineers - Physics Informed Deep Learning

sciann-applications

A place to share problems solved with SciANN

sequential_pinn

Physics-Informed Neural Network (PINN) for Solving Coupled PDEs Governing Thermochemical Physics in Bi-Material Systems

shap

A game theoretic approach to explain the output of any machine learning model.

stock-return-prediction-using-knn-svm-guassian-process-adaboost-tree-regression-and-qda

Forecast stock prices using machine learning approach. A time series analysis. Employ the Use of Predictive Modeling in Machine Learning to Forecast Stock Return. Approach Used by Hedge Funds to Select Tradeable Stocks

svshgp

Stochastic variational heteroscedastic Gaussian process