Giter Site home page Giter Site logo

Le Duc Thang's Projects

bcmo_package icon bcmo_package

We contribute here a Matlab-based optimization software package based on our novel optimization algorithm named Balancing Composite Motion Optimization (BCMO).

bcmo_package_python icon bcmo_package_python

We contribute an updated Python version of BCMO Package provided in https://github.com/ThangLe-duc/BCMO_Package. In this package, we introduce an upgraded version named Balancing Composite Motion Optimization with Gaussian Random Walk (GRW-BCMO). The corresponding Matlab version of GRW-BCMO is also provided as the release v1.1 of BCMO package in https://github.com/ThangLe-duc/BCMO_Package/releases/tag/v1.1. In GRW-BCMO, we modify the trial mechanism for determining the instant global point and the best individual via a Gaussian random step biased from the current best individual to exploit its local space. This version will solve the boundary dependency of the original trial mechanism proposed in the previous one. The proposed algorithm is constructed without algorithm-specific parameters, the users can directly apply it to solve any unconstrained optimization problems without hyperparameter tuning. The users are recommended to use Python 3.7 or more. The required libraries for using this package is numpy and matplotlib. The users can easily follow the examples with detailed instructions to implement and modify the codes for personal uses. # Contributors - Thang Le-Duc - Quoc-Hung Nguyen - Hung Nguyen-Xuan Please cite the following reference if the package is useful for your project. # References: Thang Le-Duc, Quoc-Hung Nguyen, H. Nguyen-Xuan, Balancing Composite Motion Optimization, Information Sciences, in press, 2020 https://www.sciencedirect.com/science/article/pii/S0020025520300773

hnpinn_for_pdes icon hnpinn_for_pdes

This work proposes a hierarchically normalized physics-informed neural network (hnPINN) to solve PDE problems.

smo-algorithm icon smo-algorithm

We contribute here a Matlab-based package for training deep neural networks (DNN)s based on our novel optimization framework named Sequential Motion Optimization (SMO). We select the popular MNIST classification problem to demo in this package. Some detailed definitions and instructions are also presented into the codes to help the users easily modify it for personal research and uses.

smosadam_algorithm icon smosadam_algorithm

This work proposes a Sequential Motion Optimization with Short-term Adaptive Moment Estimation (SMO-SAdam) to train neural networks.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.