no code implementations • 18 Jun 2020 • Jonathan Allcock, Chang-Yu Hsieh
We propose a quantum algorithm for training nonlinear support vector machines (SVM) for feature space learning where classical input data is encoded in the amplitudes of quantum states.
no code implementations • 7 Dec 2018 • Jonathan Allcock, Chang-Yu Hsieh, Iordanis Kerenidis, Shengyu Zhang
The running times of our algorithms can be quadratically faster in the size of the network than their standard classical counterparts since they depend linearly on the number of neurons in the network, as opposed to the number of connections between neurons as in the classical case.