REVIEW 4 cited by
Adaptive Variational Quantum Kolmogorov-Arnold Network
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Kolmogorov-Arnold Network (KAN) is a novel multi-layer neuromorphic network. Many groups worldwide have studied this network, including image processing, time series analysis, solving physical problems, and practical applications such as medical use. Therefore, we propose an Adaptive Variational Quantum Kolmogorov-Arnold Network (VQKAN) that takes advantage of KAN for Variational Quantum Algorithms in an adaptive manner. The Adaptive VQKAN is VQKAN that uses adaptive ansatz as the ansatz and repeat VQKAN growing the ansatz just like Adaptive Variational Quantum Eigensolver (VQE). The scheme inspired by Adaptive VQE is promised to ascend the accuracy of VQKAN to practical value. As a result, Adaptive VQKAN has been revealed to calculate the fitting problem more accurately and faster than Quantum Neural Networks by far less number of parametric gates.
Forward citations
Cited by 4 Pith papers
-
QuKAN: A Quantum Circuit Born Machine approach to Quantum Kolmogorov Arnold Networks
A quantum circuit Born machine can encode B-spline basis functions and trainable coefficients to form hybrid and fully quantum KAN residual functions, demonstrated on toy classification and regression.
-
Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks
QKANs show strong empirical performance on regression, vision, and language tasks, but the claimed exponential parameter reduction is not rigorously established.
-
Optimization by VarQITE on Adaptive Variational Quantum Kolmogorov-Arnold Network
Using variational quantum imaginary time evolution as a training rule can fit toy functions with a KAN-style quantum circuit, but classification performance remains worse than standard approaches.
-
The effect of Quantum Time Crystal Computing to Quantum Machine Learning methods
Adding controlled noise from a simulated time crystal improved fitting accuracy for two quantum neural network variants while degrading quantum reservoir computing, in small numerical tests.
Discussion (0). Sign in to comment.