18047397. QUANTUM COMPUTING BASED KERNEL ALIGNMENT FOR A SUPPORT VECTOR MACHINE TASK simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

QUANTUM COMPUTING BASED KERNEL ALIGNMENT FOR A SUPPORT VECTOR MACHINE TASK

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Gian Gentinetta of Chavannes-près-Renens (CH)

David Sutter of Zuerich (CH)

Stefan Woerner of Zurich (CH)

QUANTUM COMPUTING BASED KERNEL ALIGNMENT FOR A SUPPORT VECTOR MACHINE TASK - A simplified explanation of the abstract

This abstract first appeared for US patent application 18047397 titled 'QUANTUM COMPUTING BASED KERNEL ALIGNMENT FOR A SUPPORT VECTOR MACHINE TASK

Simplified Explanation

The abstract describes techniques for optimizing a quantum kernel for a support vector machine task. This involves receiving a set of training data, providing a quantum kernel with unitary operations, and performing an alignment of the quantum kernel using an optimization algorithm based on the training data.

• Quantum kernel optimization techniques for support vector machines:

   - Receive training data representing data vectors and labels
   - Provide quantum kernel with unitary operations for qubits
   - Perform alignment using optimization algorithm on quantum processor

Potential Applications

The technology can be applied in various fields such as machine learning, quantum computing, and data analysis.

Problems Solved

This technology addresses the challenge of optimizing quantum kernels for support vector machine tasks, improving efficiency and accuracy in processing large datasets.

Benefits

The benefits of this technology include enhanced performance, increased speed, and improved accuracy in classification tasks.

Potential Commercial Applications

Potential commercial applications include quantum computing services, machine learning software, and data analysis tools.

Possible Prior Art

One possible prior art in this field is the use of classical support vector machines for classification tasks, which do not leverage quantum computing techniques for optimization.

Unanswered Questions

How does the quantum kernel optimization technique compare to traditional methods in terms of performance and accuracy?

The article does not provide a direct comparison between the quantum kernel optimization technique and traditional methods in terms of performance and accuracy.

What are the limitations or challenges of implementing this quantum kernel optimization technique in practical applications?

The article does not discuss the limitations or challenges of implementing this quantum kernel optimization technique in practical applications.

Original Abstract Submitted

Described are techniques for optimizing a quantum kernel for a support vector machine task. The techniques include receiving, by digital processor, a set of training data, each member of the set representing a data vector (x) and a label (y) identifying the respective member to be part of either a first class or a second class The techniques further include providing, by the digital processor, the quantum kernel comprising a set of unitary operations adapted for acting on a zero state of qubits of a universal quantum circuit The techniques further include performing, by a quantum processor comprising a set of interlinked quantum circuits, an alignment of the quantum kernel using an optimization algorithm based on the set of training data on a primal problem approach of the support vector machine task.