A numerical library for machine learning. Various functions on machine learning (including supervised learning and unsupervised learning) are implemented in this package. Complex network can be expressed in a simple form by using data flow graphs. Efficient CPU/GPGPU parallel computation is supported to realise efficient operation on large scale data.
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 interface package to use Torch (the open-source numerical library for machine learning) from Python. Users can easily implement deep learning based on neural networks, and can use various state-of-the-art methods. This package supports GPGPU parallel computation, and realises high-speed operation. A front-end interface for C++ is also prepared.
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.
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.
XenonPy is a high-throughput material exploration framework based on machine learning technologies. This library can generate various chem/phys descriptors for machine learning to explore materials in virtual environment. Descriptors in matminer can be also used. Model training is done by PyTorch. Visualization tool for descriptor and transfer learning framework are also provided.
NetKet is an open-source project delivering cutting-edge methods for the study of many-body quantum systems with artificial neural networks and machine learning techniques. Users can perform machine learning algorithms to find the ground-state of many-body Hamiltonians such as supervised learning of a given state and optimization of neural network states by using the variational Monte Carlo method.
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.
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.
QuCumber is an open-source Python package that implements neural-network quantum state reconstruction of many-body wavefunctions from measurement data such as magnetic spin projections, orbital occupation number. Given a training dataset of measurements, QuCumber discovers the most likely quantum state compatible with the measurements by finding the optimal set of parameters of a restricted Boltzmann machine (RBM).
.