Air Force Research Laboratory, QC Ware Uses Quantum Machine Learning for Mission Applications
ROME, NY and PALO ALTO, Calif., April 27, 2021 – The Air Force Research Laboratory (AFRL) and QC Ware explore the use of one of QC Ware’s proprietary quantum machine learning algorithms to understand the purpose or the The objective of the unmanned aircraft mission by observing its flight path. Called q-means, the quantum clustering and classification algorithm can also be applied to a variety of AFRL mission applications.
QC Ware was one of the first partners to advance a key objective of AFRL – supporting the development of quantum algorithms in optimization, machine learning and quantum simulation for implementation in quantum computers at short term. The project is part of a larger AFRL effort to engage expert researchers from industry, academia and the Department of Defense to apply quantum information science to military concerns. air and space force and ensure that they remain the most advanced and competent force in the world.
âAFRL is pleased to partner with QC Ware for the development of quantum machine learning algorithms. The early and continued investment in quantum software aligns firmly with AFRL’s quantum strategy. As quantum computing hardware continues to advance rapidly and become more practical, we believe these types of algorithms will easily find applications in real-life Air Force scenarios, âsaid Dr Mike Hayduk, Director deputy of the AFRL information directorate.
âQC Ware appreciates our long term partnership with AFRL. We believe quantum software is a critical benefit for organizations and nations, and can be useful in the short term, âsaid Matt Johnson, CEO of QC Ware. âQC Ware’s research leadership in machine learning algorithms supports AFRL’s exploration of how quantum applications can ensure that US defense and space organizations maintain their superior edge.
In the first phase of the project, researchers from AFRL and QC Ware identified use cases to test and evaluate the q-means algorithm to classify the flight path behavior of unmanned aircraft. He focused on the design and delivery of software for a prototype q-means algorithm for clustering and classification that could be run on commercially available quantum computers and quantum simulators, and would have the potential to provide improved performance over conventional algorithms for a wide variety of other Airs. Missions of strength too. The team used standard software and libraries to create the q-means software to allow AFRL researchers to run and modify the software themselves.
q-means is significantly faster than its classical counterpart, k-means. Both algorithms use the same technique to group similar data points together and are especially useful when data scientists are trying to better understand the similarities of items in their data set.
Compared to k-means, the q-means approach to machine learning fits much better with more complex and large data sets. The higher the number of dimensions, the finer the granularity, which allows richer tracking of flight paths and other behaviors. The q-means method is 10x faster than k-means when clustering datasets with 64 dimensions, 30x faster on 256 dimensions, and 100x faster on 1000 dimensions.
In the second phase of the project, the research collaboration will focus on evaluating the performance of the algorithm, using real data and implementing the algorithm on currently available quantum hardware. The objective of the experiment is to determine the amount of quantum resources needed in terms of number of qubits and error rate to accelerate performance compared to classical clustering and classification algorithms.
âAFRL’s continued investment in algorithm development and benchmarking the performance of quantum machine learning algorithms against conventional algorithms, using real data and real quantum hardware, encourages efforts research on quantum machine learning, âsaid Iordanis Kerenidis, manager of Quantum Algorithms-International, QC Ware. âWe see our research collaboration with AFRL as an important opportunity to implement QC Ware’s Q-means algorithm to resolve computational bottlenecks in key mission applications.â
The Air Force Research Laboratory (AFRL) is the main scientific research and development center of the Air Force Department. AFRL plays a vital role in leading the discovery, development and integration of affordable combat technologies for our air, space and cyberspace. With a workforce of over 11,000 people in nine technology fields and 40 other operations around the world, AFRL offers a diverse portfolio of science and technology ranging from basic research to advanced research and technological development. For more information visit: www.afresearchlab.com.
About QC Ware
QC Ware is a leading quantum as a service company focused on developing applications for short term quantum computing hardware. With a team made up of some of the industry’s foremost quantum computing experts, QC Ware is growing rapidly and generating substantial revenue from global businesses and government sector clients, including the Army’s Research Lab. air, Aisin Group, Airbus, BMW Group, Equinor, Goldman Sachs and Total. QC Ware Forge, the company’s flagship quantum computing cloud service, is designed for data scientists with no quantum computing background. It provides unique and powerful turnkey implementations of quantum computation algorithms. QC Ware is headquartered in Palo Alto, California, and supports its European customers through its subsidiary in Paris. QC Ware also organizes Q2B, an annual gathering of the international quantum computing community.
Source: QC Ware