Peter P. Orth

M. Sohaib Alam, Noah F. Berthusen, Peter P. Orth

Reinforcement learning has witnessed recent applications to a variety of tasks in quantum programming. The underlying assumption is that those tasks could be modeled as Markov Decision Processes (MDPs). Here, we investigate the feasibility of this assumption by exploring its consequences for two fundamental tasks in quantum programming: state preparation and gate compilation. By forming discrete MDPs, focusing exclusively on the single-qubit case (both with and without noise), we solve for the optimal policy exactly through policy iteration. We find optimal paths that correspond to the shortest possible sequence of gates to prepare a state, or compile a gate, up to some target accuracy. As an example, we find sequences of $H$ and $T$ gates with length as small as $11$ producing $\sim 99\%$ fidelity for states of the form $(HT)^{n} |0\rangle$ with values as large as $n=10^{10}$. In the presence of gate noise, we demonstrate how the optimal policy adapts to the effects of noisy gates in order to achieve a higher state fidelity. Our work shows that one can meaningfully impose a discrete, stochastic and Markovian nature to a continuous, deterministic and non-Markovian quantum evolution, and provides theoretical insight into why reinforcement learning may be successfully used to find optimally short gate sequences in quantum programming.

Soheil Ghafurian, Peter Orth, Corey Strickland et al.

The generation of protein crystals is necessary for the study of protein molecular function and structure. This is done empirically by processing large numbers of crystallization trials and inspecting them regularly in search of those with forming crystals. To avoid missing the hard-gained crystals, this visual inspection of the trial X-ray images is done manually as opposed to the existing less accurate machine learning methods. To achieve higher accuracy for automation, we applied some of the most successful convolutional neural networks (ResNet, Inception, VGG, and AlexNet) for 10-way classification of the X-ray images. We showed that substantial classification accuracy is gained by using such networks compared to two simpler ones previously proposed for this purpose. The best accuracy was obtained from ResNet (81.43%), which corresponds to a missed crystal rate of 5.9%. This rate could be lowered to less than 0.1% by using a top-3 classification strategy. Our dataset consisted of 486,000 internally annotated images, which was augmented to more than a million to address class imbalance. We also provide a label-wise analysis of the results, identifying the main sources of error and inaccuracy.