Quantum neural networks

Kerstin Beer (Macquarie University)
Near-Term Quantum Computers: Fault Tolerance + Benchmarking + Quantum Advantage + Quantum Algorithms

Machine learning, particularly as applied to deep neural networks via the back-propagation algorithm, has brought enormous technological and societal change. With the advent of quantum technology it is a crucial challenge to design quantum neural networks for fully quantum learning tasks. In my talk I will introduce you to dissipative quantum neural networks. Functioning in a feed-forward manner, they embody a true quantum equivalent to classical neural networks and are capable of universal quantum computation. For training these networks we use the fidelity as a cost function and benchmark the proposal for the quantum task of learning an unknown unitary operation.

[ccc-gn]

Excellent talk! I have a question, in multi-layer CNNs, for each layers we always have an activation function to make the net non-linear, however, in the QNNs, all gates are unitary gates, and the output is linear result for the input. Without measurement, where are the non-linear comes from?