2DMAT is a framework for applying a search algorithm to a direct problem solver to find the optimal solution. In version 1.0, for solving a direct problem, 2DMAT offers the wrapper of the solver for the total-reflection high-energy positron diffraction (TRHEPD) experiment. As algorithms, it offers the Nelder-Mead method, the grid search method, the Bayesian optimization method, and the replica exchange Monte Carlo method. Users can define original direct problem solvers or the search algorithms.
aenet is software for atomic interaction potentials using artificial neural networks. Users can construct neural network potentials using structures of target materials and their energies obtained from first principle calculations. The generated potentials can be used to molecular dynamics or Monte Carlo simulations.
An open-source library for machine learning. Various functions on deep learning based on neural network can be used by this package. This package is especially customised for image identification, and a number of sample codes are prepared. Users can also use pre-trained models, which are open in Caffe Model Zoo. Since this package is written in C++, high-speed operation is realised.
An open-source library for machine learning. Various functions on machine learning/deep learning are implemented in this package. Using flexible user-friendly description, various types of networks from simple to complex ones can be implemented. GPGPU parallel computation based on CUDA is also supported.
COMmon Bayesian Optimization Library (COMBO) is an open source python library for machine learning techniques. COMBO is amenable to large scale problems, because the computational time grows only linearly as the number of candidates increases. Hyperparameters of a prediction model can be automatically learned from data by maximizing type-II likelihood.
CrySPY is a crystal structure prediction tool by utilizing first-principles calculations and a classical MD program. Only by inputting chemical composition, crystal structures can be automatically generated and searched. In ver. 0.6.1, random search, Bayesian optimization, and LAQA are available as searching algorithms. CrySPY is interfaced with VASP, Quantum ESPRESSO, and LAMMPS.
An application for structure prediction based on the evolutionary algorithm. From an input of the atomic position in a unit cell and possible elements at each atomic position, this application predicts the stable structure and composition from the first-principles calculation and molecular dynamics in combination with the evolutionary algorithm. This application is written in Python, and uses Quantum ESPRESSO and GULP as an external program.
An application for structure prediction based on the genetic algorithm. This application can predict the structure and composition of stable phase of crystals, molecules, atomic clusters, and so on by using first-principles calculation and molecular dynamics. This application implements interfaces with various programs such as VASP, LAMMPS, MOPAC, GULP, JDFTx, etc, and runs efficiently on parallel computing architectures.
isqpr is an R package to find candidate molecules that has your desired chemical structures and chemical properties. SMILES (Simplified Molecular Input Line Entry Specification Syntax) is employed to represent chemical structures. To find candidate molecules, sequential Monte Carlo method generates new molecules, whose chemical properties are predicted by machine learning techniques.
An open-source numerical library for machine learning. Using other machine learning numerical libraries (TensorFlow, CNTK, Theano, etc.), users can construct neural networks by relatively short codes. Since a number of methods in machine learning and deep learning are implemented, users can try state-of-the-art methods easily. This package is written by Python.