Entropica Labs Resources


Training with the Iris dataset on IBMq

Using the polyadic QML Library we trained a qmodel for the ternary classification of the Iris flower dataset on IBM quantum computers. We got the accuracy level of classical ML.

Medium post: News in Quantum Machine Learning

Watch the 15-min video presentation describing the experiment

Explore the training data: https://iris.entropicalabs.io/


The Polyadic QML Library

A Python library to define, train and deploy quantum models

The original ideas behind this library are described in a research paper: Polyadic Quantum Classifier — arXiv:2007.14044

  https://github.com/entropicalabs/polyadicQML


ManyQ quantum computer simulator

A fast quantum computer simulator optimized for Quantum Machine Learning. It uses SIMD, multicore and GPU to parallize and speedup computations

ManyQ is the underlying quantum computer simulator of PolyadicQML

  https://github.com/entropicalabs/manyq


Entropica's QAOA Library

An implementation of the Quantum Approximate Optimization Algorithm

Medium post (2019): Optimising with near-term quantum computers

  https://github.com/entropicalabs/entropica_qaoa