IBM Quantum Flex and Premium Plan users now have access to Kipu Quantum’s Rimay, a technology designed to enhance existing machine learning models with quantum feature extraction. Rather than replacing current systems, Rimay adds a quantum step to process classical tabular data, identifying additional features before returning it to conventional machine learning workflows.
This approach targets data science teams facing stalled prediction quality, and was recently deployed with a Fortune 100 company to improve customer-intent prediction. “Putting Rimay directly into the IBM Quantum Functions Catalog is an important step in making quantum machine learning easier to use,” says Dr. Tobias Grab, Managing Director of Kipu Quantum.
Rimay Integrates Quantum Feature Extraction into IBM Quantum Functions
Rimay doesn’t aim to replace established machine learning infrastructure, but instead functions as an intermediary step, processing tabular datasets on IBM quantum computers before returning enriched features to conventional algorithms. This approach targets data science teams experiencing limitations in predictive accuracy, and is accompanied by a credit-risk classification tutorial within IBM Quantum documentation. The tutorial demonstrates how to prepare data, execute quantum feature mapping and integrate the resulting features into existing machine learning workflows.
The addition of Rimay expands Kipu Quantum’s footprint within the IBM Quantum Platform, building on the existing availability of Iskay Quantum Optimizer, a service for quantum optimization problems, the company says. Rimay addresses a distinct challenge by focusing on improving the quality of information fed into machine learning models, rather than solving optimization tasks directly. The technology encodes training data into a Hamiltonian, mapping each feature to a qubit, and then runs a counterdiabatic evolution on IBM’s quantum hardware.
This process generates quantum-derived features intended to reveal previously hidden correlations within the data, potentially improving model performance. Scott Crowder, Vice President, IBM Quantum Adoption and Business Development, explains that the addition of Rimay provides an accessible way to explore quantum feature extraction that complements existing classical models, according to the company. Kipu Quantum designed Rimay to integrate smoothly with existing data science pipelines, allowing users to use quantum computing without requiring a complete overhaul of their current systems.
The service is intended to help organizations investigate new data relationships and address complex business challenges. The launch provides a practical pathway for data scientists to experiment with quantum feature extraction and assess its potential benefits for their specific applications, potentially unlocking improvements in prediction quality and model accuracy.
Putting Rimay directly into the IBM Quantum Functions Catalog is an important step in making quantum machine learning easier to use. Companies should not have to rebuild their machine learning stack or become quantum experts to find out whether quantum computing can improve a real business problem. With Rimay, the models stay unchanged, the stack stays unchanged, but the data becomes richer. For AI teams, that means improving what existing models can learn from the same underlying data, rather than simply adding more compute or complexity.
Kipu’s Rimay Enhances Machine Learning with IBM Nighthawk Processors
Kipu Quantum’s Rimay now processes data directly on IBM quantum hardware, a capability demonstrated with tabular datasets. Kipu Quantum designs its algorithms and products with current commercial quantum hardware in mind, aiming for deployable tools for enterprise challenges. The company focuses on delivering tangible business impact through quantum computing, specifically in optimization and machine learning.
We appreciate the progress Kipu Quantum is making to bring quantum computing into practical machine learning workflows. The addition of Rimay to the IBM Quantum Functions Catalog gives data scientists an accessible way to explore quantum feature extraction that complements existing classical models – and helps them investigate new correlations in their data, and move toward solving real business challenges of value.
See today’s quantum computing news on Quantum Zeitgeist for the latest breakthroughs in qubits, hardware, algorithms, and industry deals.
