QSI seminar series: Maria Kieferova - Macquarie University and Andre Nies - University of Auckland
Title: Quantum Boltzmann Machines For Generative Training And Tomography (Maria Kieferova)
Abstract: Boltzmann machines are physically-motivated neural networks used for data representation and generative training. Their quantum counterparts utilise quantum effects to represent complex data sets with compact models. In this talk, I will introduce different ways to generalize Boltzmann machines in the quantum setting and their connection to tomography.
Title: Random sequences of qubits (Andre Nies)
Abstract: Martin-Loef in a famous 1966 paper formalised the intuitive notion of randomness for infinite sequences of bits via algorithmic tests. What if we replace classical bits by qubits?
We first provide a framework to formalise such sequences as states of a suitable C* algebra. Thereafter we introduce an analog of Martin-Loef's notion. We show that for classical bit sequences the two notions coincide. We also discuss quantum Kolmogorov complexity for finite sequences of qubits and its relationship to quantum Martin-Loef randomness.
The talk will be introductory. This is joint work with Volkher Scholz.